larger batch size and steps

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -115.60 +/- 71.46
+      value: 280.00 +/- 24.62
       name: mean_reward
     task:
       type: reinforcement-learning

config.json

@@ -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 0x7f8c9c1391f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8c9c139280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8c9c139310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8c9c1393a0>", "_build": "<function ActorCriticPolicy._build at 0x7f8c9c139430>", "forward": "<function ActorCriticPolicy.forward at 0x7f8c9c1394c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8c9c139550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8c9c1395e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8c9c139670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8c9c139700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8c9c139790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8c9c13a3c0>"}, "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": 1000, "num_timesteps": 2048000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651761724.580514, "learning_rate": 1e-06, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV3QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFYvVXNlcnMvdmlrL29wdC9hbmFjb25kYTMvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVi9Vc2Vycy92aWsvb3B0L2FuYWNvbmRhMy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz6wxvegte2NhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVXAQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJboAwAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTegDhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -19.48, "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": 0.0001, "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": "macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.9.7", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.20.3", "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 0x7f80a38d8d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f80a38d8dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f80a38d8e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f80a38d8ee0>", "_build": "<function ActorCriticPolicy._build at 0x7f80a38d8f70>", "forward": "<function ActorCriticPolicy.forward at 0x7f80a38db040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f80a38db0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f80a38db160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f80a38db1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f80a38db280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f80a38db310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f80a2e72b40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 100, "num_timesteps": 10035200, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651782988.813188, "learning_rate": 0.0001, "tensorboard_log": "./ppo_tensorboard/", "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:": "gAWV1wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZkAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS2SFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 196, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 512, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV3QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFYvVXNlcnMvdmlrL29wdC9hbmFjb25kYTMvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVi9Vc2Vycy92aWsvb3B0L2FuYWNvbmRhMy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.9.7", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.20.3", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5343b01daadc1af50e1680b4b217a796b54d2d7f8c722795340f9ef96f3840d
-size 267090
+oid sha256:9d49cafba2126d5094945f4834da0e87581a257d69addf77a4b4623073c4d61a
+size 217926

results.json

@@ -1 +1 @@
-{"mean_reward": -115.59773016365943, "std_reward": 71.46422157529523, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T08:20:57.154842"}
+{"mean_reward": 279.9982176, "std_reward": 24.618676342160914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T15:26:38.553021"}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00f2e0b9a6859fea1faf6aa52a352e5355b05ffea88aee8f2562628d4cf1e0a
-size 187007
+oid sha256:18c734803c4644a5155a886cc20857dbfe9752dcbc24e8a4cc92011e44218eb2
+size 147527

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

@@ -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 0x7f8c9c1391f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8c9c139280>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8c9c139310>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8c9c1393a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f8c9c139430>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f8c9c1394c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8c9c139550>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f8c9c1395e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8c9c139670>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8c9c139700>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8c9c139790>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f80a38d8d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f80a38d8dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f80a38d8e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f80a38d8ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f80a38d8f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f80a38db040>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f80a38db0d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f80a38db160>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f80a38db1f0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f80a38db280>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f80a38db310>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8c9c13a3c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f80a2e72b40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -41,52 +41,52 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1000,
-    "num_timesteps": 2048000,
-    "_total_timesteps": 100000,
+    "n_envs": 100,
+    "num_timesteps": 10035200,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1651761724.580514,
-    "learning_rate": 1e-06,
-    "tensorboard_log": null,
+    "start_time": 1651782988.813188,
+    "learning_rate": 0.0001,
+    "tensorboard_log": "./ppo_tensorboard/",
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVXAQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJboAwAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTegDhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWV1wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZkAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS2SFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -19.48,
+    "_current_progress_remaining": -0.0035199999999999676,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 10,
+    "_n_updates": 196,
     "n_steps": 2048,
-    "gamma": 0.0001,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 10,
+    "batch_size": 512,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f74554b2ab86f8f04c772075c5e8b2d61a97985c1ddcc3400882f3557b25ac
+oid sha256:e163f133b602ce1126e0a0f127a59f693bd4ffda25b3e533872efdea19f3d134
 size 84637

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc39beaf5da1e7eae4e15cc1b1ff3b847e0f947b82ae053d358f41fae8110284
+oid sha256:caa3bc2f494d430e094275d529a3d3d6ccd2c7a4eabd1ca1e24ebf7436ac33ca
 size 43073