retry with learning_rate=0.00001, gamma=0.001, 10e5 iterations

Browse files

Files changed (8) hide show

README.md +1 -1
config.json +1 -1
replay.mp4 +2 -2
results.json +1 -1
rl-course-unit-1-ppo-lunarlander-v2.zip +2 -2
rl-course-unit-1-ppo-lunarlander-v2/data +23 -23
rl-course-unit-1-ppo-lunarlander-v2/policy.optimizer.pth +1 -1
rl-course-unit-1-ppo-lunarlander-v2/policy.pth +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -684.97 +/- 213.03
       name: mean_reward
     task:
       type: reinforcement-learning

   results:
   - metrics:
     - type: mean_reward
+      value: -70.05 +/- 78.89
       name: mean_reward
     task:
       type: reinforcement-learning

config.json CHANGED Viewed

@@ -1 +1 @@

- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f267b744050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f267b7440e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f267b744170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f267b744200>", "_build": "<function ActorCriticPolicy._build at 0x7f267b744290>", "forward": "<function ActorCriticPolicy.forward at 0x7f267b744320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f267b7443b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f267b744440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f267b7444d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f267b744560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f267b7445f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f267b78da50>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651720770.311504, "learning_rate": 0.1, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "n_steps": 2048, "gamma": 0.1, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7ad9d60290>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7ad9d60320>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7ad9d603b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7ad9d60440>", "_build": "<function ActorCriticPolicy._build at 0x7f7ad9d604d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7ad9d60560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7ad9d605f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7ad9d60680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7ad9d60710>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7ad9d607a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7ad9d60830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7ad9da1c00>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 500, "num_timesteps": 1024000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651724920.0037413, "learning_rate": 1e-05, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9j4AAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAPgAAAAAAAJoZODpjak8/6kc3PirMQL+zXa2+xc8vvgAAAAAAAAAAwOCKPXqljz/XHLM+BIdPvzOPjzzgi208AAAAAAAAAACmksE9Dfi7P+QpBD9PqKO8pc0lvq02f74AAAAAAAAAAK70jL4flKQ/x1cPv7nO576sZqE9w0eRPQAAAAAAAAAAcu8XP2OZyj+RcJ4/bZGfvgFdL78Fy1+8AAAAAAAAAABm7Zs8hKmkPukoHT5xHpO/Osu5vtr8lL4AAAAAAAAAALNRP73yLK4/Kq0sv9LrtL7TXyE9dhSDPQAAAAAAAAAAgBtjvf4cxT+BO5e+NaGCPjk6KT2jMHk9AAAAAAAAAADSk7i++uqeP2rAPb990jG/vItZPwTisz4AAAAAAAAAAJpZjjtQwr0/7K44PaVFqD7FC108VvtfPAAAAAAAAAAAmqnROrSQsz8O5CU++o63vkIN8rqTTha9AAAAAAAAAAB6+xs+YipmPthgIz4wmLi/vf71PUVqTj4AAAAAAAAAADN4bD0EHoI/65ojPuxjXr9CNii99iPsvAAAAAAAAAAAk6wrvljVrj86MiG/isW5vqREiT5tBVM+AAAAAAAAAACQstM+evR6PyswGT91/yy//pgLPu4soD0AAAAAAAAAANMtcb4vjHs/8XIqv1uuXb8qtUY/xXLmPgAAAAAAAAAAzRTDvFxRtT8yH52+ouS9PEkHOD0aQMM9AAAAAAAAAABmi0k991qvP/jzsj6x7QW+1iWavbTHib0AAAAAAAAAADZNvj6rQ+w+D1UoP62tn7+n1F++gCWIPgAAAAAAAAAANT4CPx5NjT+S9zQ/kCxBvw/Mbb5SlJk+AAAAAAAAAABmYO48N4nBP4Pokz4ljZc+p1xgvfXjOb4AAAAAAAAAAHJRDz9oUJk9ez1SP6c8tL/V+rq+6M64uwAAAAAAAAAAM8YDPYiMuT8XvsQ+DZDePcb2fr3tO0C+AAAAAAAAAABLYYS+XoFYP/qqUL96MoG/dVIOPyD2DD8AAAAAAAAAAM00IT0uhIo/eBITPvmPO7/GLr+9uli1vQAAAAAAAAAAfSABP9E3gD904JE/0yaEv8+o07/aNSu/AAAAAAAAAADuATy/ykIHPjSkgb/3qay/mDd3Ph9gnL4AAAAAAAAAAGYKbz1nrrs/W0FbPpFrNL5veDa9uozJvQAAAAAAAAAAAKZMPDJjgz/RlJo8HXEpvwezRD7OfGY+AAAAAAAAAABTbRs+R0ukP2YXDz9hEii/WNfjvjiE6jwAAAAAAAAAAIMrVL6C/BI/MBbTvheQi79TgV695oRHvQAAAAAAAAAAzflhPRB0uD/hlhs/lo/jPce4Rb3kHEC7AAAAAAAAAAAADEy8Fmi7P2PC0r1RyVY+GiQ9PRi+nz0AAAAAAAAAAM2t4j1WZq8/GwHPPgvVrr6ZlaK+VcZWvgAAAAAAAAAAW+iCvqGtTD7DocG+Sam1v9tWRD7fqsw9AAAAAAAAAAAAmHC7+QvAPi4xqD1fRq2/M5tavq/DRL4AAAAAAAAAACZ2Wj4g3LY+bkyEPi57pr/Srjo9WmWvPQAAAAAAAAAAgJlPPZGWrj/ChEI/5dGdvlc2iL2C01i+AAAAAAAAAACapcO7c4R8P2WiLr0fc0O/d/dZPupE8D0AAAAAAAAAALPxNL0//qs//UHlvoubzb6niOw82aQjPQAAAAAAAAAAwDvRvkg8Wz8QRni/CzNovy50WD+mBgI/AAAAAAAAAACqesg+pH2dP14NQz/tYiq/OH+DvntjpD0AAAAAAAAAABXs276wPMo/sE56vxz8pr5DsSQ/9L6RPgAAAAAAAAAABr5qPmBmjD+meB8/z7syvy64lzywxCw+AAAAAAAAAADmvwU9azixP1fwmD5+gFq+T3rSvOwHhD0AAAAAAAAAACP8Rz9kfIQ9CRMYPyZ64bzfz+6+dnlTPwAAAAAAAAAALZBnPk9tkD/uYo8+BZYzvyY2BD8TkXQ+AAAAAAAAAAD6KG4+6G6oP4qJIz/1Rfe+F3/PvlptUb4AAAAAAAAAAJolfTwoTrM/d2RGP+Ptcr7uGIC8FAsIvgAAAAAAAAAAlgKQvs0mcj4upeO+KX68vxlcH77X24G+AAAAAAAAAAAAwLc7uy3HPxYMOTxDQZ0+2PGdvB4Hqj0AAAAAAAAAAM4Njr4bCig//m0/vx4ii7/4Eso+tvnmPQAAAAAAAAAAZtYfvRW3rz96IUy/c8ymvgawOj3tGTU+AAAAAAAAAAAzCJo+KKXGPX6RHT8/NMS/D+kCv/Jwsb4AAAAAAAAAAADgJTvmQr4/7m8SPNwlTj6xRg09YMraPQAAAAAAAAAAZi4CPI6Dsz9iBk4/ULPAvim8Fry2qzq+AAAAAAAAAAAAnli8C6e+P5baor0G2pI9ejAevVNqDT0AAAAAAAAAAE37tT4Thk8/Nv1WP5MxXr/tACi/PhaSvgAAAAAAAAAAJljXPXsPxD+2RoU+OtQHvqqI3L1vYwU8AAAAAAAAAADmH5A9vbN5P6gLFj4S31S/+6bAPOMbX70AAAAAAAAAAKDWar9776g7Ey2ovjP8P74uTDE+emidvwAAAAAAAAAAjTiYPoZFET9omAs/ikaQv4CPC75BNbk9AAAAAAAAAADqMxa/N3GAvSO0lb9gIbC/xPg8P0bK3D0AAAAAAACAP61V2D6o+p0/Sn9vP2vRKL8c+zi/1aGzvgAAAAAAAAAAs9U5vjWcyT9tC/W+p0AEvhQ70L3CH8y9AAAAAAAAAAATLyQ+4ajXP1Yg6D4jz5e+YXsSvy3Kzb4AAAAAAAAAACb+H79gmEc/2KVWv/7khL9ul6Y+59UhPQAAAAAAAAAAMzFIvHzgwj/Bvwa+CfztPpUsWD0ZZC0+AAAAAAAAAACYZz6/zUGavVW8Ur2Z7Ya9wIC1Pl5GFL8AAAAAAAAAAOaodz6XlYo+3aPNPjrOk79bkTi+fvbHvQAAAAAAAAAAYuSuvqskUD8Cx1q/czJUv7uMED+elYU+AAAAAAAAAABm7lo9rs6mPft3974sbDi+LjILQACBIUAAAAAAAAAAAEN1mD5JbYA/NR5HP9+XHb+ehXe+QNvOvAAAAAAAAAAAza/0PM3fuj+ml98+GvFsPv3nH726oQO+AAAAAAAAAACzeMU9SABnP5ow5j3s3V+/9+dtPnqOgT4AAAAAAAAAAGCj9j5gY0Y/QlCdPwlQU7+oPyS/X/SKvgAAAAAAAAAAZrbju/rgBD+bCS09O86ivxrsib3G3oG+AAAAAAAAAACdXM4+DUQBP/jiLD+h2Iq/Mbmfvt5V4b0AAAAAAAAAANoljD6zy10/++5eP68CVr/bsMC+rpqBvgAAAAAAAAAAZkjZPASjqz5SazU+Ygyiv1p63b4TsVe+AAAAAAAAAACmTww+L2GtPyE4MT/sKRe+21o/vqnePL4AAAAAAAAAAKa2071gSL8/aW8Gv8WPiDyiago+VYf2PQAAAAAAAAAAzcQWvPvDmT/fU7O8AykmvyDS87yCGya9AAAAAAAAAABmrKo8N4mpPw83wj2b/6q+NonFvDZuazwAAAAAAAAAAAD3A754n7M/3vsCv6+4rr5BoyQ/AlWNPgAAAAAAAAAA7c14Pn42Xz8j8lw/HoaGv6ILeb6qCiC+AAAAAAAAAAC7B+O+7xFRPjszLb/kfqy/vC1ZvkCq/b0AAAAAAAAAACDkLD50daY/1RkrP9pPyb6Jmxq+LtFIvQAAAAAAAAAAppgEv5yN0T7NW42/SvKPvwpnYz/qrgs+AAAAAAAAAACAfj89Llu9P7j+Fj/7/LQ+y88OvckBB70AAAAAAAAAAEpmkj4ooaM//V1MP6MN2r59PN6+vq2rvgAAAAAAAAAAiqZkv59I2D4r7sq/7HF7v1wfST9Kl+M+AAAAAAAAAACNZK89rhTlPSrsLb1siK2/nIQAPxe0Sz4AAAAAAAAAADOafD1oGrk/OkpQP2oxRD7IL6e9ZolZvgAAAAAAAAAATSUVv8NxSLyw/1a/kTmVvgm/QkBG3CtAAAAAAAAAAADTRD4+UbRoPp3j7j7HRbm/wOl+vi0LdL4AAAAAAAAAAI2Cg70/ma8/Qkcov6sZSb6fzYs9EYYfPgAAAAAAAAAADZHoPWcHSj/jQHc+nQV4v40fUT0Yo9o9AAAAAAAAAADTjzO+Y3h3PxbBhr5r916/wCp/PlDnQz4AAAAAAAAAAIB2GT7itLo+TS3jPgWrj7/DEcG+2eQzPQAAAAAAAAAAnZvhvtVogD+yp1K/ZrMlv2wwgD7jRkY9AAAAAAAAAACamby7WMO1P+4+Fb/WKM8+08LaO8Q5Bz4AAAAAAAAAADPqDL7wqFs/zMOevoSlYb/PkLe9OLnUvAAAAAAAAAAArgMJP9vyLT+eE44/xstOv0l0XL7d6Mw9AAAAAAAAAAAAhtu9KESKP1HFA771sh+/RX2dvQGrAL4AAAAAAAAAAHohkD5TLQk/PV02PxxXn79wS+q+wqqcvgAAAAAAAAAAACvvvKhhtT9bn66+rJIOPJYigz0csh4+AAAAAAAAAADmpqe9M+OzP4agg757VY2+/gC+Peb5Wz4AAAAAAAAAAP5aA7/8HaA/RIGMv/sCAb+BOg8/dioVPgAAAAAAAAAAQvn0vl4kQD+z/pG/SzSRvxYjoj/2a/s+AAAAAAAAAAAgQ7o+BBKmPyrjlT87n5K+X3Q9v3b+v74AAAAAAAAAAE2zl73TT+4+PSIMveDGhb9d/Gi+UR6duwAAAAAAAAAA5lc1vVzNrT/ANfy+kPG0vu5wiz0bq/o9AAAAAAAAAAAAAJ86GSqjP0ajBzwasRi/ocNjPRkinT0AAAAAAAAAAMCInT1pGX0/DoxlPj2+TL/aK7C9nagGuwAAAAAAAAAAs4RXP4P6qD4FjjY/VH23v+05rD6+hqk+AAAAAAAAAAAmnzg+cw+vPzjd6T6DgeG+3RBSvmB+/L0AAAAAAAAAAFDEPT9L0Tw//OquPxVekb9WcIu/kH5YvgAAAAAAAAAAs9++vc8sUD+oCs2+thNqvxfMFD8GnKk+AAAAAAAAAADTyge/I9bwPkmHFr8kr4m/zCwbvtXW3r4AAAAAAAAAAAAdyr0WdKM/9bPEvueoA78LD0Q+OIz3PQAAAAAAAAAAGhlEPSenij/ifwM+5jEkv8YsVD0c7qk9AAAAAAAAAAAA8AE9692sPx6cDT+StAO/s9hxvfkxgr4AAAAAAAAAAACiRr34wMA/4tiGvkOKCD5Xrby7oA7CPQAAAAAAAAAAmrhlvd4iIj+ersS8S/11v6X98L0SUrq8AAAAAAAAAABAeoo9+V1vP6xqwj2UnVO/W0HEvQ/JmL4AAAAAAAAAACZjID8Vp+E+KeqDP8Fvt7/fvMG/dEOvvgAAAAAAAAAAJriBvqUTTT96dvm+IaRtv/Salj76IKs+AAAAAAAAAABy6AK/+gpsPtrFT78BzK2/TM02P5WJgj0AAAAAAAAAAGDGcj5J15c/hlFIP5IZFb8Zt7O+E2tgvgAAAAAAAAAA9tzXPn9ixb0BOq48QxHTvGCloT1K9Oa8AAAAAAAAAABmCvO7YI2yP+H8hr2qXxq+s3SyPIIFpT0AAAAAAAAAAJprNby9pJU/KvO1vXwVZ7/mHSM8YMWQPQAAAAAAAAAABvUQvgdfvz+T9hG/2y+TvQqehj7e0os+AAAAAAAAAABaqgS+d3KuP+683r6dHaK+PpicPu/cEj4AAAAAAAAAAFZ9rD6986M/no5VP1QLF7/1xi2/djq8vgAAAAAAAAAAZgzmvJ/jkD9boRS+sxsFv3I49z13fBw+AAAAAAAAAAAAiTu+uINSP2JXCb/7pna/PWM0PoWHRj0AAAAAAAAAAH31AT/XBCk/op8OP0GGi7/d8w0/f7aePgAAAAAAAAAAOoWhvgyy2D/Vh22/ksz7uVF3Lz/JU6k+AAAAAAAAAAAz4sC+5B+vP5vVc7+N4c6+XagRPxDHVT4AAAAAAAAAABpSOz+3HzQ/2o+SP2ZJjL+NbE6/1uwDvwAAAAAAAAAAU9NmPqytgz8WDR0/jxNGv7ijD7+Dmbi+AAAAAAAAAADAlXc+3mVXP0C06j7HmTq/D3uHvqe2Ab4AAAAAAAAAAA0wKr6zemo/r5iLvoMsZb9BigG7EBH1PQAAAAAAAAAAgzu7Pp5QrT/5vrg+qo8Bv1cHqj5k7oQ+AAAAAAAAAACtwkI/1GKcvMonnz/goY+/C03bvkNoUT4AAAAAAAAAAGZiVLyaabE/5afvvfkhRL7FvoQ9Xh27PQAAAAAAAAAAzg/+vnAj7T6NkmG/VIqDv9fkSD4lAwE+AAAAAAAAAABNiQe98fKPP3JuE752vR6/xrcPPg4MSD0AAAAAAAAAAJpxWjsrjvE+VcwLvueDZ78aJYA+EnBtPgAAAAAAAAAA1Uvevqe+Zz6d4zm/nIebv0vxhD7Ibja8AAAAAAAAAAAARYE+u7iBP/+fCT/XT06/c+mxvlq4u74AAAAAAAAAAGb6ozsvor0/SGxyPded1D1pFq29i1B8vgAAAAAAAAAApn/mve9SAT8K+8m9kKaRvxhrJ75y80i+AAAAAAAAAACz/m0+FsKUP/Ck9j7dfza/GSeovhLOHr4AAAAAAAAAACZenD7aqYg+Ff5JPw7ns79GkBW/8zKevgAAAAAAAAAASgFyvguMAD9eoNO9A4e1vyXkyr7EgiS9AAAAAAAAAABmP5O8/NCyP/4DG7/EoWO+9FWqPBmUDT4AAAAAAAAAAE1nnz48dt0+Qm8pPwWSp79Wm969Kib6PQAAAAAAAAAAhjM1Pn/FvD+g6A0/Un5PvRrAhLyThH89AAAAAAAAAACz3CQ9IlG8P5he0z6b7hc+50ivvck6Nb4AAAAAAAAAADMWGb7/eMI/Gwc5v8dzZz09oJI9tVWvvAAAAAAAAAAAjXKLvYfMjj+Pi0u+NFkTv10fJz4wEx4+AAAAAAAAAACadSa8nF6zP4w6sb6/lSy+fcBuPDbf2j0AAAAAAAAAADPkhryleZM/WinNux0D/L748788ZB+cuwAAAAAAAAAAs0wWPaTIsT9CIgc/AfQ+vgjWIb0puAS+AAAAAAAAAADN01M+yLm5P4tjFz93ynu+J2TCvsXGiL4AAAAAAAAAAEA9kb27pq0/q8qcvoArmr7HZYw+YP1wPgAAAAAAAAAAMyKuveQLoj8grfC+5zrkvmYZOz7o11E+AAAAAAAAAADzpsw9Yr25P4iC0T4fskS+xYxKvqDIX74AAAAAAAAAAGt0Ej/1LAc/hRicP8rRhb+vKia/wnncvQAAAAAAAAAAzaqUPBPlez+3Eso9M5Agv/hzZL6tu9S9AAAAAAAAAADN6Vg9i+68P1SnKD+Aco0+GmFmvSjO2r0AAAAAAAAAABD9jj65HSk/emwjP+EsgL9OkhW+2nFQvQAAAAAAAAAAs0mWvjdzcT8YMW+/IPJBv8qs8j5UrpY+AAAAAAAAAACzehk9Sop1P/7kiD3ktje/FEXMPaadGD4AAAAAAAAAAFrdbz+kh5A+ZjTNPwCjwL9yg8i/odW5vgAAAAAAAAAAzV5AvsbA0z5Fq3m+LB2Nv1Cpbb77cAi+AAAAAAAAAACanWS9Jdm/Pw4xOL58lHE8wqO8vZJNHL4AAAAAAAAAAHN68j3JJYc/CGTxPrIjLb9msRG/G+WcvgAAAAAAAAAAbZ14vgrkwD+E+Em/u+bzvI6xfz7S3b89AAAAAAAAAABToAs+DRa5P7ZZHT8Poay9SWeGvYESlL0AAAAAAAAAAIDyGT37mrg//d4JP4MoCj4bfia9iGdmvQAAAAAAAAAAsEoNP39hOT8Nl1Q/wvV0v0bMH76uJyK9AAAAAAAAAAAmVIc+WBdePxmeGz+85Ge/1oDtvn5O070AAAAAAAAAABqBlL2VP1U/x6SEvmCxR7+LtSM+nFTBvQAAAAAAAAAAikEoP0KkjT+KgI0/Prkzv7XHhb4GC5I9AAAAAAAAAABGxac+RXH5Ps5KBD+JMY+/0vKvvo3ysb0AAAAAAAAAAHqKPz5PQ6A+tgC2Pm+Yk79WMzi+oP/QPAAAAAAAAAAANfCqvvz/QD3bR8U9vL4Bvvkx6j7ejw+/AAAAAAAAAABvODO/VOWYP3KPm7+Bpzi/O6woPypqy70AAAAAAAAAAC1yGz7Ls8A/jbpXPmtnrL5eqd09LsYaPgAAAAAAAAAAM7EnPpO2yT8qjM8+JdRPvkOKEr4dQbm9AAAAAAAAAACGY64+tgywP16SYT+dJUO+D9livq2Yjr0AAAAAAAAAAGYl0r1Td64/2PITv1u5jL7wPhE+zVmiPQAAAAAAAAAAyo2xvpMKMT+OfS6/UQptv5tBkD7gdtU7AAAAAAAAAAA6FEw+O8FnP5PIoz7Z0FS/PPuGPqcEMz4AAAAAAAAAAE3Lvj3qTYs/TvQ7PufxGL84Q0a9svJFvQAAAAAAAAAAnYvGPpSMVz6NDlg/6xKLvxHlE7/mJce9AACAPwAAAADNerg87PKzP77DQT+5WdC92BXmvIddMb4AAAAAAAAAABqUUL2qkpE/DfZLvv8PQ79rKcI9MQkkPgAAAAAAAAAANoGZvhw7cD/7Wze/wJhov73Omz2OM/Q9AAAAAAAAAABgEpu+n+gPPkWSBb8KyqK/lYYsPi42vjwAAAAAAAAAADrtE760CYu8gmmBvbAOqb9dlCA+XY/ovgAAAAAAAIA/M1aTPFCxsT++Co47abfcvu5WaT7H/SE9AAAAAAAAAABpJGm/YGk6PzoUyr+8I3q/bXpyP7gm1j0AAAAAAAAAAADkej29CKI/0ndrPskv3L4UGuG96KYPvQAAAAAAAAAAmtKyPrTn7D7dNfI+SeCIv6gLgrz+28u5AAAAAAAAAACA+Ka9RpWsPzBLBb8U0l++FEfDPQ9yDj4AAAAAAAAAAKbZ7T0OVqs/TddSP3cinb5bXA6+CIlMvgAAAAAAAAAAGhbWPZpRgT96ldw+JCpdv//lCL5wNW++AAAAAAAAAAAGM9A+vkv/PubbNT9sy6O/4EhOvzN3gr4AAAAAAAAAAPOzhz0imKU/0p/KPooV3770jqa8efHHvAAAAAAAAAAAc7CTvQpoGT/O0UW+YiCTv+/9jj6iaqk9AAAAAAAAAABNwOo9jtGaP9690D6mHA+/mOYfvmpXub0AAAAAAAAAAIC6Vz7pFSs/XnAZP3opjb+EHi2/vYznvgAAAAAAAAAAoMuOPmWwwT/FWEg/5ztUvlu31L0uKvE8AAAAAAAAAAD6MBK+Phi6PxBi1b5Mi3m+fjMgPPlTPr4AAAAAAAAAADM4uj00rrs/61lRP2aLIz627SK+qnquvgAAAAAAAAAAbTTJPsARrz6lbh4/7kWNv13uNb5wIgs+AAAAAAAAAABmZLy82L6xP1CVSL8eora+FZzoPD3pXj4AAAAAAAAAAPNpdD48Vro/XbQJPzpCuL4emF69maIoPgAAAAAAAAAA6+wNP7w2nj+eT1Y/F50xvxrzmr6e3yS+AAAAAAAAAABzvOG9o82vPppGsb4PGqK/FNQDPzbphj4AAAAAAAAAAJp2Xz3ca8M/gWzBPkm/az7Nhoy9ULj4vQAAAAAAAAAAznvkvtb0LT8tt52/h7GGvwjPRj/Ch5U+AAAAAAAAAACD2mq+eCbIP0ORC7/puB2+Tgv6vbt5Q74AAAAAAAAAAJJfDr+ryFk/cFNuvwNOab9gy+g+9m85PgAAAAAAAAAA4F5QPlqapD9DAz4/nMcFv41G0r0zoyG9AAAAAAAAAACaUfq9WoxUP82j576+lEK/b6vyPvhzDj4AAAAAAAAAAApw1T6rGHc/L4AzPz+uX78FjZg+H321PgAAAAAAAAAAoxgrP27MDb6KcJo/ZMKvvylyGr8mV/29AAAAAAAAAADN6hS9jG+CP82Ct7x/BDi/uTA6vkLHXr4AAAAAAAAAALbEJ79EJIg/y+qTv/2udL/sOVg/azciPgAAAAAAAAAAzQyHOyCvlD+qj648iQM4v7P6HD1IPJs8AAAAAAAAAAAGpM4+WSapPvYDZz+Xaai/Q1jevgDker4AAAAAAAAAAPMoiD11X60/LpL/PhcCi77984e9Zq8VvgAAAAAAAAAA/T6nPmZ0Pz/A4FQ/53N6vxCNiL7l5XM9AAAAAAAAAAB+6aO+2xROP0iN+L6Z3Hq/uGAdPUiwy7wAAAAAAAAAAEphkT50Ehs/ABCvPnVle79R98g9hgwfvQAAAAAAAAAAv+oXv4ly9j5+E2e/I3qUvxh6IT7Lpme9AAAAAAAAAACa7vE9aFWcPgiR0z4Eq52/ehszv27Jib4AAAAAAAAAANpaDT4QLsU/JptEP8t/PT7c6ly+rNImvgAAAAAAAAAAu3njvqlsDD/2tGG/Mq2Pv8Y4Dj8FM/c+AAAAAAAAAADF6Nm+L1MwPxqIZ78/iGi/35ABP+bOZD4AAAAAAAAAAGZXDT3IO6c/ht38PKCN676g9pk+645ePgAAAAAAAAAAzVQ9O0DktD/2z5U+VPHQPfXwWrs2vYe9AAAAAAAAAACaDcC7A57SP27ww7wcsog+AIwIPaPM/D0AAAAAAAAAAPuoQb9MCJS9uDRuv7NF+L7spC8+NN0oPwAAAAAAAIA/M4dAvVYpqD8MP7a+7ui9vverWT03RZ48AAAAAAAAAAAA0Ly6YCuzPyFwFb627f2+trDbOlpmBz0AAAAAAAAAAMivhr7VmI0/PzI9v0CdFL/OzOs+zkOLPgAAAAAAAAAAYFslPmqeqT9jQUc/XsGAvqogcb4Dxl++AAAAAAAAAAD6jyO+Y9JSP2aE676Sf4u/hLZnPkucmD0AAAAAAAAAAJ2Xtb4MuV8/NyYlv4BrXb8FNJE+HiE5PQAAAAAAAAAAgM73Pix14j7vTkg/XWh+v0W8Lb6Fr+29AAAAAAAAAABzdHo+pC8kPw5nJD/Uhpi/gqkUv5VRe74AAAAAAAAAANC75D4YtqQ/GHb0PpcrP78zv4A+U+LMPQAAAAAAAAAAGoCEvY3gpD/d3dG+KaTUvvw2j7y62lu9AAAAAAAAAAD8M12/svVEP2i83L+jSYO/B9qrPzEolj4AAAAAAAAAAAAVQz0I+70/ThPNPmSGJD4FI0u9KicYvQAAAAAAAAAAugJdPjcdcT8hOkU/b9Zbv0dOv76BK5O+AAAAAAAAAACNtsM9W8+nPh/gsz2nr5u/bW4SPe543j0AAAAAAAAAAJpY5T1PDm0/Q47GPUKNQr8YmEs+JwudPgAAAAAAAAAApi0mPjKxrD9QuAU/FpqnvrhH0r4W94G+AAAAAAAAAACVDcG+nO7cPmqDlb5mOJS/nJAIv2PiFr8AAAAAAAAAAMaoU74mWJc/Rpclv6S1Eb/zNQY++TSFPQAAAAAAAAAAYlycvmdcYj+E/Ay/Nb1Nv2jr4L2mPGO+AAAAAAAAAADaSU8+jiQuP66iiD4pT1q/fucUPnPkAT4AAAAAAAAAAF0LHz8Ki4I/sj47P5VcgL/yUlm+FTKZPgAAAAAAAAAA+oobPoWNdD9bfbI+N1sMv8wCAL7fMUq9AAAAAAAAAABmrYm9O76jP6KaG7+gFRu/HDmKPbhTDT4AAAAAAAAAALOb6r1ZR6g/GnsNv93L3b7x03I+MJxyPgAAAAAAAAAA6JlNv8Gx5T4wy9G///+1v0DFuz+VtaY+AAAAAAAAAACGCEI+Eg2xP0eIGj/LUzy+ntFLvt2RfzwAAAAAAAAAADN5pb0U0IE/9SZjvsKpRb9l8IU+zYDWvAAAAAAAAAAAZgEuPa07nz97LVk+cAHivoCh4b4LldG+AAAAAAAAAAA3HSO/1zFDPmu0ir/nWq+/TyhpP/tSZz0AAAAAAAAAADbxGj9TMQM/9Z6JP0eMkb/PPDu/7dlivgAAAAAAAAAADEgEv1vRiz8xGZO/PsRFv2O5jT/CMgQ/AAAAAAAAAACoh6G+4DefP3zlSL97JxK/0IK5PpK4Bz4AAAAAAAAAAF0n6z43kEg+dS+QP1eHpL9/JoW/BdekvgAAAAAAAAAA5hMqPWUovj+UTbQ+at1EPu2+or32wjC+AAAAAAAAAABaxbU9bSGXP5Skvj65siC/EmJZvo47mb4AAAAAAAAAABrgwT3Y27I/FO0LP3EWJL71cZ+9/WjlvAAAAAAAAAAAGtqavcGrxD9b5Hu+usUJPRZ5/byefLi9AAAAAAAAAAALBwg/VDonvbr5qz1Odcm9AVbdvgIgRj8AAIA/AAAAADMadz4KTYM/RP4GPyb0O78l+cO9r3o/PQAAAAAAAAAAmmuXvTy2rz/yQgu/Mz9svuqZnj2m7oY9AAAAAAAAAAAA8nu95XkcP7lUGr5/bmO/R1hbPj5HND4AAAAAAAAAADMuC70sj6k/nKOwvoI4+b7QnRQ80tnfPAAAAAAAAAAAAgCKvgmUhz+Z6QC/bM8/v5M+yz5rLHc+AAAAAAAAAABTVgM//O9JPq/Iyz69M5S9ULwAwI2X+r8AAAAAAAAAAM2Hoj49npI/QncVP7CxKb/jzBW+i5DCvQAAAAAAAAAAmsOuPYQpnz9gBA0/+d0ev6PvvL1Zlyi+AAAAAAAAAADG3gI+nFc3P6GHvD1rRmm/uT9sPjMwuz0AAAAAAAAAACYtHj8kLks/WP2VP4GOiL+l5nu/9oH+vgAAAAAAAAAAwMkCvrIOyT/SO2K+Wlwwvq1VRr4zSJO+AAAAAAAAAAAKHBA/Y1ItP76oij+zqG6/Db0Zv92Qf74AAAAAAAAAAIYSnL7H7+c+tT76vo6pqb+laLq8sk+CvQAAAAAAAAAAbSkkv3/2iL0idrG/OQfJv2dwjT9o2tk+AAAAAAAAAABmBoG+QCOMPyWrOL+PNUa/pUuLPm4SQj4AAAAAAAAAAE0zVT0doww+uHmxvlWjpb9SKzM/+ai6PgAAAAAAAAAAZoUlvda3rD++8S6/YiP4vrp6ND3YRMU9AAAAAAAAAABzhRW+yBddP0YWy77amoi/7UHKPmnlnT4AAAAAAAAAAPD2+j622Dk9RnueP0Ptlr9t+ou/nuk8PgAAgD8AAAAAxnYYP2dWKT/dxu4+rc9/v2NsgLxdZ7e9AAAAAAAAAADanyU+a+QqP3+nBT+ZPp2/DOjVvq53lL4AAAAAAAAAALOKtD436pk/pqMvP8YeGb/OlHW+PsBXPQAAAAAAAAAARp8nPn5rnT9wHR4/7O3TvngJOL4Goz++AAAAAAAAAABmRW29gcrGPyVhab4DsfG9rkxwvCwSBD4AAAAAAAAAAGZpX70HTVw/II/jvV00QL/bYLW8S3f8vQAAAAAAAAAA5VO7vh1cZT+PjCW/kUd+v9zH9T4lZZU7AAAAAAAAAAB7h8G+I/1bPZNSZ79/mpG9PsrFPw6ELEAAAAAAAACAPza3wL6oR9c9lEcsv+5Ir78PAPo+tuZ/vgAAAAAAAIA/CJjcvtXVfj86rAe/mpNWv1L1zr3gEy2+AAAAAAAAAAAahGk+tDGXPppHIz75Kam/Vgh5PrCA67sAAAAAAAAAAB+YKb/By749ucSMvxR7t78g4mY/2OjsvQAAAAAAAAAAUJJqvgoFNruhgwm+fEy2vzlb475AoLM9AACAPwAAAABmE6M8mPC6P8Ensz7PoZk+QKOQvN1/9L0AAAAAAAAAAHrdLT75yFg/4FbvPnfvar+eb3S+vEdHvgAAAAAAAAAAIM4dPvTtzT6mO58+FnKqv00vgL52Gnw9AAAAAAAAAABmSlK9tr+HP1bKUL6dKmC/1K1AvNIfQ70AAAAAAAAAAGbCSL33D3Y/tp/DvkD/Nr/J4UQ/1RSdPgAAAAAAAAAAs83IPfIKxj/GWw0/R2ZzPizAob01fQO+AAAAAAAAAACGd0k+KZaNP6MaZj8hYDC/SzOLvv6gcr4AAAAAAAAAAG1LNr6Nhag/h8cXvzPmur6EldA9DTITPgAAAAAAAAAAzbiKO2Ygtj+uRQc+NOsZPhNmhjm/QRo9AAAAAAAAAAATLcA+n6SEP778RT+/ayi/h16ZvapBLz4AAAAAAAAAAABp9LyEJaw/AJGlvXuOr74AYjC9DnCGvQAAAAAAAAAA86kNvhvFhz+Baq6+/dFCvxBOjj1SD929AAAAAAAAAABN+CQ+/OGTPw+WRz+hvRm/Emv2vdIA0L0AAAAAAAAAABq6Ib0U37g/GR0EvsBbe75CWEa+AE/YvQAAAAAAAAAAwACHPfCYKT89p24+myiQvxYN/r7lQLW+AAAAAAAAAAAGqgE/K/kzP1SDiD+MLnS/xHANvzVeKL4AAAAAAAAAAOaB8D2egJA/WuXAPqLsF7/KzYa+6kRsvgAAAAAAAAAA2nPxvehXrj+9IVS/caSCvnurTz5WiKA+AAAAAAAAAACN9Lg+S7tXP+P4cD8LIGy/GE8Nv6x6Lb4AAAAAAAAAAKYYgj1TtLQ/Lv6UPt5FBr5BHyK8Zb6zPQAAAAAAAAAAzfhYvKt5Mz9WSRC+tzBgv/hE9j3vqws+AAAAAAAAAAAAeAq7f0iiP0dwFbtN9QW/i0k5PGfuOL0AAAAAAAAAAABuUjxwakQ/eJmyvL62jr+uQOQ9s5x2PgAAAAAAAAAAEwQZvoUbCD/TmmG+phyGv2SZxb3qOzE+AAAAAAAAAAAgemk+dJ5NPi7TPD88R6u/QLGFvyPOsb4AAAAAAAAAAE3FMD2Ahro/mwrZPpdaAD6Xn7e9MMpevgAAAAAAAAAAwNdlPso+sT92C4A//4+8vZV8uL7nCLu+AAAAAAAAAAAzYK+8jPW9P7WLQb4uqHg+uX0zPXbHoD0AAAAAAAAAADO477z0ha0/wCIXv9KtBb/wdus8vC8LPgAAAAAAAAAAmA+4vsIulz9i72+/vvMFv3FT/D6C348+AAAAAAAAAABgDwY/PhaJP1Nrbj+19mO/A5cQv39Ulb4AAAAAAAAAAA3Cpj7DurI/BmhNPwyPxr4DCN2+JXfpvgAAAAAAAAAAxmfKPv0csT91yVQ/0IGQvixZhr6+t0Y9AAAAAAAAAACK2JS+PEGBP7M8Jb9D6zO/fDX8PQkAtj0AAAAAAAAAAE8xHb8iDgs+bXCVPeRA0b4kLStAe4opQAAAAAAAAAAA81ZTPjh/zz6GIbU+elqXv7Hoi71/iqm9AAAAAAAAAACNWYG9v/G2Px1LAr/c+yO6gKvbPZaKcD4AAAAAAAAAAHsUBb9A9Ks/6Jsbv7vBIL9Mm52+PZ6XvgAAAAAAAAAAANInvRtYfz+V9vq95QFDvzkBKT4kMkY+AAAAAAAAAADNHAE9YMy3P6f4uz1Hj7q+hoLmPIouzz0AAAAAAAAAAM1kOT4iTT4/YEnXPvAQgb+LyqM9rrqdvQAAAAAAAAAA8zz+PV4ehT/0nac+JqdAv06m3L0a9MG9AAAAAAAAAACTzq6+ocnCP0rpdr/K8nC+wvUBP2FtmD4AAAAAAAAAAOIDhL71j5w/uC79vstJL78N7qs9C5rIuwAAAAAAAAAAQLV0vml6lj+VixC/XfEfvwzuBD/k254+AAAAAAAAAADaew0/dP+vP4cuhj866BO/b0Utv8usgr4AAAAAAAAAABr1h70Pra0/iygmv78/qr5zT/89AuqnPgAAAAAAAAAA2rKivW6umz/YsrC+OUwQvxzKRj3uXYm9AAAAAAAAAADWM50+VIJWPlPcDT8vvqG/Y4m1vqU4f74AAAAAAAAAAI3VYr+fjtE+isydvxY1mr9Esck+FqIcvgAAAAAAAAAAzTeWPBHcrz9qpI4+YBqOvjqxpbzxv4i9AAAAAAAAAACAB2s9cjuyP0KvIj8qpCq+oWYYvcqih70AAAAAAAAAABryQz74cwQ/KG/NPmDymb8forS+hqfCvAAAAAAAAAAAEBIcv6nBFj81PSy/cgCFv3FZ4DwQOeG9AAAAAAAAAAAzayQ9lCm0PxNOKj+aDru9cnQ2vX7o0b0AAAAAAAAAAE1kqD3jI88/kqaSPiYvTr2gKTW+A/QXvgAAAAAAAAAADcm7PV6roT+KDWk+f1Y3v1ValL6Hhoi+AAAAAAAAAABG3xO/1pJfPWWp5bzfFoK8Q0BKPSCtMz0AAIA/AAAAAD42Ab8vOhg/o1aCvy11m7/CU3I/eCeWPgAAAAAAAAAA05nQvsGKiz7dXWi/xPapv/3NeT9Cc2c+AAAAAAAAAADzWQu/IVeCPeh+rb9zgJ2/xx+AP0Haxz0AAAAAAAAAALro2D5cb249EDM7P7Wds79hM4m+2mQHvQAAAAAAAAAAft8XP34cgz0tQvs987yZPUVaUr9BDAvAAACAPwAAAAAm5pk+Mg+WP9vJ0z7pNDK/6Dp2PlVdfz4AAAAAAAAAAGY3hj6UZbo/4RccP1bYSr5aEIe+ymAEPAAAAAAAAAAAM0szvHWOsT963ZO+7GGNvgOp0js1ojI9AAAAAAAAAAC61aA+1COpPwD4Tz+A8+y+hWPLvdCvvToAAAAAAAAAAMP/Br9ylus+WECNv1CHqr/VxoA/tKsBPwAAAAAAAAAAGqR8vdgIoD/f0KO+dBf+vhyQzz32LQg+AAAAAAAAAADNIYo9bnIwP1h2kT7qpWm/EprwvoBjFb4AAAAAAAAAAE1tRT397LU/RkNUP350sT2DuHS9eFNPvgAAAAAAAAAAkHbMvqY1rj96Ak6/UyuSvq2aWj3jj1S8AAAAAAAAAAC+cua+ZBnDP3PAkL+3QoK+BWNsP31cHj8AAAAAAAAAAAT1SL8wLfI+aRiDvzHcj78I05U+OsboOwAAAAAAAAAATda8vQ01pD8q38a++uCBvqnupD3C0ba6AAAAAAAAAAAAtbk9NJKeP5cZCL4cVQy/jKwgP3P99D4AAAAAAAAAAEb6WL73Z48/ZlHjvkLTOr8R1wE/mXKzPQAAAAAAAAAAmrlgOnBgsj8zbDA8we5HvjYW77oG5qa8AAAAAAAAAACaGSI8TTWoPy9jHj79hyG/O8h0vHmgHb4AAAAAAAAAAMqccb6M0Hw/kFgev5d8W79z1yc/vm6uPgAAAAAAAAAANl+nvg/uCT+1QCq/tWidv301Bj/neB8+AAAAAAAAAABGnwi+lGqnPw6n476s0N6+rSsZPqbrQj4AAAAAAAAAAI3zI77nb8o/1Eyxvlfik74MmZo+rlGePgAAAAAAAAAAs1+jPcY0xD/eqbs+DS8AvbEy2L1ucbS9AAAAAAAAAABa9CM/cWMAPisLRz/qeay/BlP2OUtNwjwAAAAAAAAAAMBKHb4HcIA/Ivsuv6p9db8mNTw+QYBMPgAAAAAAAAAAWh69vZi2zD/+qky+ulaZvm0OKL1aKaK8AAAAAAAAAAAD9aM+eL+VP7qfHj8TlFW/YTzvvsk8pb4AAAAAAAAAAAARy7wmUbk/RwQev5TQwT5UxKg8nplhPQAAAAAAAAAA6izSvqFt9z3uSya/D1aav68rez1CsT2/AAAAAAAAgD8AuT6+y18cPwxyBL+p95S/EqTwPueZjT4AAAAAAAAAALPGnL3vtSM/q0N6vcL9Wb+Q6Uu+PkAGvgAAAAAAAAAAiv7XPr7SjD8dWlA/EuNdv8zsc7/iq62+AAAAAAAAAADVrs6+BlNLPyoKRL+xOW+/h88WP6diBj0AAAAAAAAAAOMIa77xQy0+yNiKPMmDpL/pqRq/0y7NvgAAAAAAAAAAmplDOVKKdj9C9He9AtBiv/NgkT4tUJs8AAAAAAAAAACAYoY9slW6PyKNHz8l5gk+WMzfvYrKUr4AAAAAAAAAAJox77zFK7w/rT/OvnyHyD56PQY90lGRPQAAAAAAAAAAMxTqPCAAyD8KQG09LnMbvf7lij055jw+AAAAAAAAAADdr9w+lMkCPiBTHj/DzMe/RaZav8upjL4AAAAAAAAAAMaRgT4DmE4/6P+bPjr2S7/BjRc+1fwfPgAAAAAAAAAAmlLGPiVSAz9V63c/Yl6mv1iPH7/eSqG+AAAAAAAAAADA/q49LmqyP1AG8T6mpxC+39fjvUu2wL0AAAAAAAAAAMBEBD4R9Kk/xokQPnUw0r70eQw+9+kavQAAAAAAAAAApf+GvmwDgD8grbC+vnw9v6zNDr2WGWO9AAAAAAAAAACarQA8P227P0crBD5+aqg+M3thOw05hzwAAAAAAAAAACYCTj6UowM/xKu2Pl1Jkr9lXHM9/lv8vAAAAAAAAAAAM4G6PdhMwT/QEH0+OShHvq0wzL3i2iO9AAAAAAAAAABmeri7Zqm7P8x/tb2gH5c+hUCHOe6huDwAAAAAAAAAAMAajr1gf7c/o+buvluElb3tOj0+AsiMPgAAAAAAAAAADdzXvdleYT+4fTy+bCg2v4mz7bsIDXO9AAAAAAAAAABNJT69L1eFPsLqMj2v2p+/xKuOvlUcHb0AAAAAAAAAAACFxL2tlgM/FRSovZEFm7/8JYW+9v5FvQAAAAAAAAAAzRCxvMYQoj65g749zrqqv0WnH78SraG+AAAAAAAAAACNEt89bG6lP1q9vD66RuG+6xabvW++zD0AAAAAAAAAANpfgj1q068/Mj42PkRug76i68I8bXfcvQAAAAAAAAAAAG4vvPy4vD8L8Um9XSC6PVCHBb0PpLu9AAAAAAAAAACa52A8kvqyP/8Xij5qZSm+VvphvPpVx7wAAAAAAAAAAKDINz5c+jK8XvvPPlUZm7/8Nea+Qtj3PgAAgD8AAAAAzUVPPR/gtT/3eZM+0ygFvu0Ynb0RXim9AAAAAAAAAAAmUjm+B2wfP5KYzr67rVu/82TXPeXZZD4AAAAAAAAAAAoqTz9B9Cw+Il/EP5YZxL9eZbu/KiCXvgAAAAAAAAAAs5gJPZOxfz8MwA0+7KJRv69+K75oR9C9AAAAAAAAAAAmOye+X6uFPK5VZL5J17+/gV00voomhL0AAIA/AAAAAM2auz38CIQ/gKyOPm9vRr+S+169B5ubPQAAAAAAAAAAPcoAv8HF+D66uF+/SxiOv71ZxD6mBYw9AAAAAAAAAAAmL2U+LRdwPx39Lj+Hyn2/cO2OvdqBGT4AAAAAAAAAAOfIDr8OXYc/aIF9vyL0T7+pShs/miK7PgAAAAAAAAAAgA5fPgHVqz969cI+LlsRv/y9qL7gqFY+AAAAAAAAAAAzm087cgKkPwOs5DsSbPq+RxR6PVvL8z0AAAAAAAAAAFN6Pb5t97Q/rmnjvn918r74WSk/fdPYPgAAAAAAAAAA/WkZP7MaWD8PcpQ/mkuIvwh7nr9miKa+AAAAAAAAAADAte+9QyqiPwvIqr7GjbS+0FGIvD+ICb4AAAAAAAAAAJP8ij6dlRA/IuolPtwpl79MGA4/w6UTPgAAAAAAAAAABg4BPnRSgD92xag+tf5Iv6E6Tj4t1Gw+AAAAAAAAAACdSZi+T1sDPabJv76pOaW/+Vr7vR1fJrwAAAAAAAAAAB7Kpr6NbV8/5/dKv1KmVL/iPjA/6DyKPgAAAAAAAAAAzW17PSnH6T4B7Cg+gq+tv6ET8r4SQ/i9AAAAAAAAAABzbBo+C9zRPQFjLz5QRby/cVpFPkiYhrwAAAAAAAAAAFrerj3KwzQ/3lRLPv6Ki78VkAw+gcysPAAAAAAAAAAAmpBBvigpmD+VMOC+r2zUvmNLyz1lyl48AAAAAAAAAABzj4c9b1aiPzVVdz6WTuu+eZ+tuzr06LwAAAAAAAAAAIAFLL3n5kI/HhmtvbosVL9r5Xi9i7rNPQAAAAAAAAAAzWvxvCqHsT+2H4u96eG7vvGBXb4aune+AAAAAAAAAAAau3s9F4sQPEXaob1j+ry/9hHDPlIW0D0AAAAAAACAP+aM8z32Qqw/rdkOP5ooxL7MHgS+Gr3IvQAAAAAAAAAAm3OSvvZo+z6iJsq+F3yQv3UMib6i0QW+AAAAAAAAAACAaAS9YwWoP/9jNb4bGty+ad49Pp8Nnj4AAAAAAAAAAJoFYz6pixM/hTUQPwn7jb+dVlq8FlGHvQAAAAAAAAAAAJvKPBZzuT/GFwA+yn9rvbCopbw7J5E9AAAAAAAAAAAAtxK+gz5UP+a12r5X9WW/DTwbPqQtuDwAAAAAAAAAAEDvF75XuCE/pk6fvRv+j7+kpcC+8wNtvgAAAAAAAAAAmjr2PuFejT2mwiY/n2zBv+jobT5dIHI+AAAAAAAAAACAdsE9V6K2P9MWxj7Fq9i9C4kovtKxf74AAAAAAAAAAC1WEb57jmY/aUsJv4DpZL/tYKM+hMKAPgAAAAAAAAAAKQRFv1IiPz/XNba/NfSSv37CsD8GCLA+AAAAAAAAAADN/BO7ISC0P7g6ar6q6ie+YO0rO8I5VD0AAAAAAAAAAOqWOD/1izY/lTKWP+fyp7+nmbe/F9eLvgAAAAAAAAAAABLTvbvNJj+OQJi+iReFvzbI1z6t9Zo+AAAAAAAAAAAdE6o+fi2tPwqWTz9aWO2+FtcJv664nb4AAAAAAAAAAM28fT7KtTM/BRA7P3Aclb8ImqK+WnK3vgAAAAAAAAAA5od7PeQLyj8ta2k+8Pk1PdeiFb4GhoW8AAAAAAAAAAAAYUu+8oOqP0wrsr57Wf6+p7GdvJK3hr4AAAAAAAAAAEaWyT72zKU/m7J1P3IQ0b4Cg+m+cgyMPQAAAAAAAAAAbpG4vuTatT8A23K/Q8ixvsoaKD+XFcY+AAAAAAAAAABGYAK+IEcJPxrcj77ULYy/OItVPbACaj0AAAAAAAAAAHk6G79BbVQ/s4ebvx9/eL8qnnc/LU98PQAAAAAAAAAATS0rvQYlIj+NfR2+sXGEv/Gx1D1KOM89AAAAAAAAAAANN4Q9HvCKP73agz4QYlS/mIYlO5BPeb0AAAAAAAAAAGZ0Fzwl7Ys/tn03PSkgTL9srgi94cyCvQAAAAAAAAAAZhA9vEqYmj8Y3lY+m3wHv4T7JL+mrOS+AAAAAAAAAABaNeU9Wbq/P/4CUj+76yE++2IJvrJAf74AAAAAAAAAABoGIz3G5sE/GyEcPoF5jDx/KCO9rv+VPQAAAAAAAAAAzUJFvnY/sz8ohTa/1wlNvp3pGbz6+i6+AAAAAAAAAACNC569uM7DPytFuL6SHPc8mOR1PVonvj0AAAAAAAAAAM0NJT1urfU9JfuqPF3Hs78U4Fg+NGc5PgAAAAAAAAAAjdsDvtQEkD9utg6/DUoXvx0EIj5gSF49AAAAAAAAAADNca88WhusP0s4Ez52aJ6+ioH1vHsrdL0AAAAAAAAAAF7ug76cJdA+Uq4Wv7V2n7+vtLY+p4xFPgAAAAAAAAAApliLvrBpgD/0hBa/FKFbv+JHiT5+bGI9AAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiTfQBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.001, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

replay.mp4 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e883841d72f363d25d44fd3c78458d059a8e529a2e3c3bb4ea0902f8661a43
-size 124089

 version https://git-lfs.github.com/spec/v1
+oid sha256:23f4fb1525095315fb7a549826e9a0ce630ef834d5d4184286552e367e79c746
+size 275235

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": -~~684~~.~~9681381363422~~, "std_reward": ~~213~~.~~03110475006937~~, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-~~05T03~~:51:03.~~759138~~"}


1	+ {"mean_reward": -70.05350927585968, "std_reward": 78.88752551964075, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T05:02:02.106257"}

rl-course-unit-1-ppo-lunarlander-v2.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7546a7cdbc0cafb344f2357866cc48a17fa8b3d65bcb15954e5811da7122f902
-size 143984

 version https://git-lfs.github.com/spec/v1
+oid sha256:d738b121f61d5b2bb507ce0ee5b1d7f3c7081f864162316cd7324da3c4fee1bd
+size 165276

rl-course-unit-1-ppo-lunarlander-v2/data CHANGED Viewed

@@ -4,19 +4,19 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f267b744050>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f267b7440e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f267b744170>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f267b744200>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f267b744290>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f267b744320>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f267b7443b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f267b744440>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f267b7444d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f267b744560>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f267b7445f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f267b78da50>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -41,43 +41,43 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
-    "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1651720770.311504,
-    "learning_rate": 0.1,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 310,
     "n_steps": 2048,
-    "gamma": 0.1,
     "gae_lambda": 0.95,
     "ent_coef": 0.0,
     "vf_coef": 0.5,

         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7ad9d60290>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7ad9d60320>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7ad9d603b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7ad9d60440>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f7ad9d604d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f7ad9d60560>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7ad9d605f0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f7ad9d60680>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7ad9d60710>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7ad9d607a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7ad9d60830>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f7ad9da1c00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
         "dtype": "int64",
         "_np_random": null
     },
+    "n_envs": 500,
+    "num_timesteps": 1024000,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
+    "start_time": 1651724920.0037413,
+    "learning_rate": 1e-05,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
+        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVaAIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJb0AQAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYk30AYWUjAFDlHSUUpQu"
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
+    "_n_updates": 10,
     "n_steps": 2048,
+    "gamma": 0.001,
     "gae_lambda": 0.95,
     "ent_coef": 0.0,
     "vf_coef": 0.5,

rl-course-unit-1-ppo-lunarlander-v2/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f38eda0e39362a57a5da485de2ea767f24d949d7cd0c9bc51e4d4209835bc86
 size 84893

 version https://git-lfs.github.com/spec/v1
+oid sha256:272ac4e6ddca329f2057613b1a068f01c788af6be82e1c4b8893f30f2ac545ad
 size 84893

rl-course-unit-1-ppo-lunarlander-v2/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e39d8a730eb8d38c7fbcd37d2d223e59e57406b14277b34008736213d007008
 size 43201

 version https://git-lfs.github.com/spec/v1
+oid sha256:5872d6a63fa91bcc0a567641d5e43138a54b77132e22f390f8441254e38accfd
 size 43201