second model
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +33 -30
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 281.03 +/- 15.99
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f890e616c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f890e616ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f890e616d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f890e616dc0>", "_build": "<function ActorCriticPolicy._build at 0x7f890e616e50>", "forward": "<function ActorCriticPolicy.forward at 0x7f890e616ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f890e616f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f890e61c040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f890e61c0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f890e61c160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f890e61c1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f890e61c280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f890e617570>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677906629471648535, "learning_rate": 0.0003, "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": 124, "n_steps": 1024, "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": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f26e3df04c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f26e3df0550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f26e3df05e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f26e3df0670>", "_build": "<function ActorCriticPolicy._build at 0x7f26e3df0700>", "forward": "<function ActorCriticPolicy.forward at 0x7f26e3df0790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f26e3df0820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f26e3df08b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f26e3df0940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f26e3df09d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f26e3df0a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f26e3df0af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f26e3de4de0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVkgAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": 4, "start": 0, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677963249691136668, "learning_rate": 0.0003, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIjX+fcWHTcUCUhpRSlIwBbJRLpowBdJRHQMH653RXwLF1fZQoaAZoCWgPQwiOW8zPDfFyQJSGlFKUaBVLx2gWR0DB+vVWZJCjdX2UKGgGaAloD0MIILJIE+9lX0CUhpRSlGgVTegDaBZHQMH6++uvECN1fZQoaAZoCWgPQwjwoq8gzUlwQJSGlFKUaBVLqWgWR0DB+wN/x2B8dX2UKGgGaAloD0MI5C8t6pPKb0CUhpRSlGgVS6FoFkdAwfsH1W8yvnV9lChoBmgJaA9DCL6+1qUGOXNAlIaUUpRoFUvRaBZHQMH7EKMm4RV1fZQoaAZoCWgPQwjwp8ZL90NyQJSGlFKUaBVLhGgWR0DB+xJlcyFgdX2UKGgGaAloD0MIPPazWEp6c0CUhpRSlGgVS7poFkdAwfsUoGY8dXV9lChoBmgJaA9DCAxYchWLC3JAlIaUUpRoFUuTaBZHQMH7F3rt3Oh1fZQoaAZoCWgPQwikObLySw5yQJSGlFKUaBVLw2gWR0DB+yWhh6SldX2UKGgGaAloD0MIrMlTVlMbb0CUhpRSlGgVS5BoFkdAwftH0QK8c3V9lChoBmgJaA9DCHiXi/gOFnJAlIaUUpRoFUu8aBZHQMH7T9OIqLF1fZQoaAZoCWgPQwhEwYwpmMRyQJSGlFKUaBVLumgWR0DB+1JylvZRdX2UKGgGaAloD0MIYTQr2weicUCUhpRSlGgVS8doFkdAwftZQZXMhXV9lChoBmgJaA9DCOJZgoxALnJAlIaUUpRoFUu/aBZHQMH7ZAVGkN51fZQoaAZoCWgPQwjl7QinxaBxQJSGlFKUaBVLqGgWR0DCCMn99+gEdX2UKGgGaAloD0MIyEEJM+0wcUCUhpRSlGgVS6VoFkdAwgjRDm8ujHV9lChoBmgJaA9DCJ8gsd396nJAlIaUUpRoFUvKaBZHQMII0Mz2vjh1fZQoaAZoCWgPQwgzp8tios5xQJSGlFKUaBVLwmgWR0DCCNlbs4T9dX2UKGgGaAloD0MI0jqqmuBlcUCUhpRSlGgVS7NoFkdAwgjgLCvX9XV9lChoBmgJaA9DCGMnvASnwnJAlIaUUpRoFUv3aBZHQMII5YQBgeB1fZQoaAZoCWgPQwj3kVuTbrdyQJSGlFKUaBVLxGgWR0DCCOonSfDldX2UKGgGaAloD0MIDI/9LNbickCUhpRSlGgVS7toFkdAwgj31bJOnHV9lChoBmgJaA9DCOAPP/89XHFAlIaUUpRoFU0eAWgWR0DCCRXIGQjmdX2UKGgGaAloD0MI8bvplt22cECUhpRSlGgVS8BoFkdAwgkgi9qUNnV9lChoBmgJaA9DCIfddwxPwHFAlIaUUpRoFUuzaBZHQMIJKM5wOvt1fZQoaAZoCWgPQwjBqQ8kbzpyQJSGlFKUaBVLymgWR0DCCTP1FpfydX2UKGgGaAloD0MIHsGNlK3PckCUhpRSlGgVS85oFkdAwglLJDmbLHV9lChoBmgJaA9DCJXVdD0RmnJAlIaUUpRoFUumaBZHQMIJU0RnOB11fZQoaAZoCWgPQwgfhIB8CctzQJSGlFKUaBVL92gWR0DCCVYOH310dX2UKGgGaAloD0MINxYUBmXCckCUhpRSlGgVS8BoFkdAwglgNYKYzHV9lChoBmgJaA9DCNLj9zZ9mnFAlIaUUpRoFUumaBZHQMIJYo7vG6x1fZQoaAZoCWgPQwgwnkFDf3VzQJSGlFKUaBVLxmgWR0DCCWtuJk5IdX2UKGgGaAloD0MI1/Z2S/IxcUCUhpRSlGgVS6doFkdAwgltgQ6IWXV9lChoBmgJaA9DCKW762wICnRAlIaUUpRoFUvEaBZHQMIJcdZ7ojh1fZQoaAZoCWgPQwiVu8/xEVlzQJSGlFKUaBVLs2gWR0DCCXGD8LrpdX2UKGgGaAloD0MIOgX52Ui5cUCUhpRSlGgVS4NoFkdAwgl8D3/PxHV9lChoBmgJaA9DCOV/8nfvvnJAlIaUUpRoFUvRaBZHQMIJm5vUBn11fZQoaAZoCWgPQwgWiJ6UiTRwQJSGlFKUaBVLkWgWR0DCCaQTZg5SdX2UKGgGaAloD0MIlwFnKVlKcUCUhpRSlGgVS6loFkdAwgmkdzXBg3V9lChoBmgJaA9DCLtemiLAqnFAlIaUUpRoFUuzaBZHQMIJtMjVx0d1fZQoaAZoCWgPQwjuPsdHi/9xQJSGlFKUaBVLq2gWR0DCCc5vUBn0dX2UKGgGaAloD0MIgZICC+APcUCUhpRSlGgVS4xoFkdAwgnWs052hnV9lChoBmgJaA9DCJSgv9AjRXBAlIaUUpRoFUuraBZHQMIJ2PmYBvJ1fZQoaAZoCWgPQwjXNO84RZVyQJSGlFKUaBVLtWgWR0DCCd35vcagdX2UKGgGaAloD0MIVvMckS9ucUCUhpRSlGgVS5VoFkdAwgnfschkiHV9lChoBmgJaA9DCAXhCihUxXJAlIaUUpRoFUuYaBZHQMIJ5g5imVJ1fZQoaAZoCWgPQwj6l6QyxTtxQJSGlFKUaBVLvWgWR0DCCfBEWqLkdX2UKGgGaAloD0MI0GBT51E2Y0CUhpRSlGgVTegDaBZHQMIJ/J9Aood1fZQoaAZoCWgPQwgm4q3z73lzQJSGlFKUaBVLwGgWR0DCCgSESM99dX2UKGgGaAloD0MI56vkY3f3bkCUhpRSlGgVS5poFkdAwgoai0OVgXV9lChoBmgJaA9DCFZkdEASE3JAlIaUUpRoFUvyaBZHQMIKG0QCjlB1fZQoaAZoCWgPQwhMbD6uzcpxQJSGlFKUaBVLrWgWR0DCCiFXmvGIdX2UKGgGaAloD0MIsYf2sQLTb0CUhpRSlGgVS6RoFkdAwgoiNz8xbnV9lChoBmgJaA9DCNdrelCQrnRAlIaUUpRoFUveaBZHQMIKJ4yXUpd1fZQoaAZoCWgPQwh8YMd/wV9xQJSGlFKUaBVLrGgWR0DCCk8d5prUdX2UKGgGaAloD0MImBQfn5DxcUCUhpRSlGgVS6JoFkdAwgpPslb/wXV9lChoBmgJaA9DCBR3vMmvMXBAlIaUUpRoFUuiaBZHQMIKYAnMMZx1fZQoaAZoCWgPQwhFSN3OPsZwQJSGlFKUaBVLrmgWR0DCCmDtXxOMdX2UKGgGaAloD0MIB+qUR7c9ckCUhpRSlGgVS+VoFkdAwgphlGwzL3V9lChoBmgJaA9DCKZkOQmla3BAlIaUUpRoFUucaBZHQMIKZeQ2dd51fZQoaAZoCWgPQwjG+3H75cZzQJSGlFKUaBVLzWgWR0DCCnm5lOGkdX2UKGgGaAloD0MIWW3+X3VsS0CUhpRSlGgVS3toFkdAwgp89nscAHV9lChoBmgJaA9DCMHKoUU2ZnNAlIaUUpRoFUvraBZHQMIKiN0FKTV1fZQoaAZoCWgPQwhE96xr9AFwQJSGlFKUaBVLpGgWR0DCCpTFZPl/dX2UKGgGaAloD0MI6iPwhx+lckCUhpRSlGgVS6NoFkdAwgqU1NQCS3V9lChoBmgJaA9DCAoQBTPmoXNAlIaUUpRoFUvNaBZHQMIKlie/Yap1fZQoaAZoCWgPQwjLLEKxVYJzQJSGlFKUaBVLoWgWR0DCCpnWJ79idX2UKGgGaAloD0MICttPxriucUCUhpRSlGgVS6FoFkdAwgqexJNCaHV9lChoBmgJaA9DCCgqG9aU6XJAlIaUUpRoFUvmaBZHQMIKrrj5sTF1fZQoaAZoCWgPQwhy3ZTyWhdyQJSGlFKUaBVLlmgWR0DCCs8FwDNhdX2UKGgGaAloD0MI5e0IpwVkcUCUhpRSlGgVS61oFkdAwgrP0QK8c3V9lChoBmgJaA9DCCE6BI4ELk5AlIaUUpRoFUuXaBZHQMIK1JvHcUN1fZQoaAZoCWgPQwgLQnkfxx5zQJSGlFKUaBVLzGgWR0DCCua+SKWLdX2UKGgGaAloD0MINV1PdB00dECUhpRSlGgVS7doFkdAwgrmv7m+03V9lChoBmgJaA9DCJI9Qs2QQEtAlIaUUpRoFUt4aBZHQMIK7ScTakB1fZQoaAZoCWgPQwhNEHUfALdwQJSGlFKUaBVLpWgWR0DCCvSNXHR1dX2UKGgGaAloD0MIr1qZ8AvGckCUhpRSlGgVS9JoFkdAwgr5Zdv863V9lChoBmgJaA9DCBOaJJZUO3JAlIaUUpRoFUu+aBZHQMILAkl/pdN1fZQoaAZoCWgPQwhBn8iTJFdwQJSGlFKUaBVLpGgWR0DCCwmKjzqbdX2UKGgGaAloD0MI3WCow0qjcECUhpRSlGgVS65oFkdAwgsRGR3eN3V9lChoBmgJaA9DCCxmhLdHZ3JAlIaUUpRoFUvBaBZHQMILI1nVXmx1fZQoaAZoCWgPQwj5LxAECJ9wQJSGlFKUaBVLo2gWR0DCCyQJ1JUYdX2UKGgGaAloD0MIdXRcjazJckCUhpRSlGgVS79oFkdAwgsnkwvg33V9lChoBmgJaA9DCFK69C9JGXNAlIaUUpRoFUvjaBZHQMILK/pD/l11fZQoaAZoCWgPQwhIjJ5baFNiQJSGlFKUaBVN6ANoFkdAwgtKwcHW0HV9lChoBmgJaA9DCCL/zCC+V3BAlIaUUpRoFUuQaBZHQMILTAy2x6h1fZQoaAZoCWgPQwhW8rG7gDlwQJSGlFKUaBVLq2gWR0DCC04F1SwXdX2UKGgGaAloD0MINjy9UtbScUCUhpRSlGgVS8BoFkdAwgtWUyHmBHV9lChoBmgJaA9DCKj91k7UjnFAlIaUUpRoFUumaBZHQMILWgMlTm51fZQoaAZoCWgPQwhNFCF1e0FxQJSGlFKUaBVL0WgWR0DCC2d/+bVjdX2UKGgGaAloD0MIE2OZfkmac0CUhpRSlGgVS6NoFkdAwgtzmNBF/nV9lChoBmgJaA9DCIe/JmtUeXNAlIaUUpRoFUu8aBZHQMILealchTx1fZQoaAZoCWgPQwi1wvS9hlZ0QJSGlFKUaBVLs2gWR0DCC3vnIQvpdX2UKGgGaAloD0MIZoUi3Q95cUCUhpRSlGgVS7VoFkdAwguRZ26kI3V9lChoBmgJaA9DCMPTK2UZJnJAlIaUUpRoFUu0aBZHQMILm0Gu9vl1fZQoaAZoCWgPQwjpEDgS6PtvQJSGlFKUaBVLnGgWR0DCC6gEfT1DdX2UKGgGaAloD0MIkQn4NZIUQ0CUhpRSlGgVS6doFkdAwguxuwX67HV9lChoBmgJaA9DCIGyKVd4EHFAlIaUUpRoFUuuaBZHQMILvgwoLG91fZQoaAZoCWgPQwhY/nxb8C9xQJSGlFKUaBVLhWgWR0DCC8VNL128dWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 920, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.97, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "False", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8598950496863d467181e9b1de86145fa6ec2b4bea8c0ff8bdf838f6d181de9c
|
3 |
+
size 146933
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,60 +4,63 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
"observation_space": {
|
25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
-
":serialized:": "
|
27 |
"dtype": "float32",
|
|
|
|
|
28 |
"_shape": [
|
29 |
8
|
30 |
],
|
31 |
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
-
"
|
34 |
-
"
|
35 |
"_np_random": null
|
36 |
},
|
37 |
"action_space": {
|
38 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
-
":serialized:": "
|
40 |
"n": 4,
|
|
|
41 |
"_shape": [],
|
42 |
"dtype": "int64",
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
-
"num_timesteps":
|
47 |
-
"_total_timesteps":
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
-
":serialized:": "
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,27 +70,27 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
80 |
"n_steps": 1024,
|
81 |
-
"gamma": 0.
|
82 |
-
"gae_lambda": 0.
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f26e3df04c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f26e3df0550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f26e3df05e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f26e3df0670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f26e3df0700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f26e3df0790>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f26e3df0820>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f26e3df08b0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f26e3df0940>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f26e3df09d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f26e3df0a60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f26e3df0af0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f26e3de4de0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
"observation_space": {
|
25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
"dtype": "float32",
|
28 |
+
"bounded_below": "[False False False False False False False False]",
|
29 |
+
"bounded_above": "[False False False False False False False False]",
|
30 |
"_shape": [
|
31 |
8
|
32 |
],
|
33 |
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
34 |
"high": "[inf inf inf inf inf inf inf inf]",
|
35 |
+
"low_repr": "-inf",
|
36 |
+
"high_repr": "inf",
|
37 |
"_np_random": null
|
38 |
},
|
39 |
"action_space": {
|
40 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
41 |
+
":serialized:": "gAWVkgAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
|
42 |
"n": 4,
|
43 |
+
"start": 0,
|
44 |
"_shape": [],
|
45 |
"dtype": "int64",
|
46 |
"_np_random": null
|
47 |
},
|
48 |
"n_envs": 16,
|
49 |
+
"num_timesteps": 1507328,
|
50 |
+
"_total_timesteps": 1500000,
|
51 |
"_num_timesteps_at_start": 0,
|
52 |
"seed": null,
|
53 |
"action_noise": null,
|
54 |
+
"start_time": 1677963249691136668,
|
55 |
"learning_rate": 0.0003,
|
56 |
"tensorboard_log": null,
|
57 |
"lr_schedule": {
|
58 |
":type:": "<class 'function'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_obs": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "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"
|
64 |
},
|
65 |
"_last_episode_starts": {
|
66 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
70 |
"_episode_num": 0,
|
71 |
"use_sde": false,
|
72 |
"sde_sample_freq": -1,
|
73 |
+
"_current_progress_remaining": -0.004885333333333408,
|
74 |
"ep_info_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIjX+fcWHTcUCUhpRSlIwBbJRLpowBdJRHQMH653RXwLF1fZQoaAZoCWgPQwiOW8zPDfFyQJSGlFKUaBVLx2gWR0DB+vVWZJCjdX2UKGgGaAloD0MIILJIE+9lX0CUhpRSlGgVTegDaBZHQMH6++uvECN1fZQoaAZoCWgPQwjwoq8gzUlwQJSGlFKUaBVLqWgWR0DB+wN/x2B8dX2UKGgGaAloD0MI5C8t6pPKb0CUhpRSlGgVS6FoFkdAwfsH1W8yvnV9lChoBmgJaA9DCL6+1qUGOXNAlIaUUpRoFUvRaBZHQMH7EKMm4RV1fZQoaAZoCWgPQwjwp8ZL90NyQJSGlFKUaBVLhGgWR0DB+xJlcyFgdX2UKGgGaAloD0MIPPazWEp6c0CUhpRSlGgVS7poFkdAwfsUoGY8dXV9lChoBmgJaA9DCAxYchWLC3JAlIaUUpRoFUuTaBZHQMH7F3rt3Oh1fZQoaAZoCWgPQwikObLySw5yQJSGlFKUaBVLw2gWR0DB+yWhh6SldX2UKGgGaAloD0MIrMlTVlMbb0CUhpRSlGgVS5BoFkdAwftH0QK8c3V9lChoBmgJaA9DCHiXi/gOFnJAlIaUUpRoFUu8aBZHQMH7T9OIqLF1fZQoaAZoCWgPQwhEwYwpmMRyQJSGlFKUaBVLumgWR0DB+1JylvZRdX2UKGgGaAloD0MIYTQr2weicUCUhpRSlGgVS8doFkdAwftZQZXMhXV9lChoBmgJaA9DCOJZgoxALnJAlIaUUpRoFUu/aBZHQMH7ZAVGkN51fZQoaAZoCWgPQwjl7QinxaBxQJSGlFKUaBVLqGgWR0DCCMn99+gEdX2UKGgGaAloD0MIyEEJM+0wcUCUhpRSlGgVS6VoFkdAwgjRDm8ujHV9lChoBmgJaA9DCJ8gsd396nJAlIaUUpRoFUvKaBZHQMII0Mz2vjh1fZQoaAZoCWgPQwgzp8tios5xQJSGlFKUaBVLwmgWR0DCCNlbs4T9dX2UKGgGaAloD0MI0jqqmuBlcUCUhpRSlGgVS7NoFkdAwgjgLCvX9XV9lChoBmgJaA9DCGMnvASnwnJAlIaUUpRoFUv3aBZHQMII5YQBgeB1fZQoaAZoCWgPQwj3kVuTbrdyQJSGlFKUaBVLxGgWR0DCCOonSfDldX2UKGgGaAloD0MIDI/9LNbickCUhpRSlGgVS7toFkdAwgj31bJOnHV9lChoBmgJaA9DCOAPP/89XHFAlIaUUpRoFU0eAWgWR0DCCRXIGQjmdX2UKGgGaAloD0MI8bvplt22cECUhpRSlGgVS8BoFkdAwgkgi9qUNnV9lChoBmgJaA9DCIfddwxPwHFAlIaUUpRoFUuzaBZHQMIJKM5wOvt1fZQoaAZoCWgPQwjBqQ8kbzpyQJSGlFKUaBVLymgWR0DCCTP1FpfydX2UKGgGaAloD0MIHsGNlK3PckCUhpRSlGgVS85oFkdAwglLJDmbLHV9lChoBmgJaA9DCJXVdD0RmnJAlIaUUpRoFUumaBZHQMIJU0RnOB11fZQoaAZoCWgPQwgfhIB8CctzQJSGlFKUaBVL92gWR0DCCVYOH310dX2UKGgGaAloD0MINxYUBmXCckCUhpRSlGgVS8BoFkdAwglgNYKYzHV9lChoBmgJaA9DCNLj9zZ9mnFAlIaUUpRoFUumaBZHQMIJYo7vG6x1fZQoaAZoCWgPQwgwnkFDf3VzQJSGlFKUaBVLxmgWR0DCCWtuJk5IdX2UKGgGaAloD0MI1/Z2S/IxcUCUhpRSlGgVS6doFkdAwgltgQ6IWXV9lChoBmgJaA9DCKW762wICnRAlIaUUpRoFUvEaBZHQMIJcdZ7ojh1fZQoaAZoCWgPQwiVu8/xEVlzQJSGlFKUaBVLs2gWR0DCCXGD8LrpdX2UKGgGaAloD0MIOgX52Ui5cUCUhpRSlGgVS4NoFkdAwgl8D3/PxHV9lChoBmgJaA9DCOV/8nfvvnJAlIaUUpRoFUvRaBZHQMIJm5vUBn11fZQoaAZoCWgPQwgWiJ6UiTRwQJSGlFKUaBVLkWgWR0DCCaQTZg5SdX2UKGgGaAloD0MIlwFnKVlKcUCUhpRSlGgVS6loFkdAwgmkdzXBg3V9lChoBmgJaA9DCLtemiLAqnFAlIaUUpRoFUuzaBZHQMIJtMjVx0d1fZQoaAZoCWgPQwjuPsdHi/9xQJSGlFKUaBVLq2gWR0DCCc5vUBn0dX2UKGgGaAloD0MIgZICC+APcUCUhpRSlGgVS4xoFkdAwgnWs052hnV9lChoBmgJaA9DCJSgv9AjRXBAlIaUUpRoFUuraBZHQMIJ2PmYBvJ1fZQoaAZoCWgPQwjXNO84RZVyQJSGlFKUaBVLtWgWR0DCCd35vcagdX2UKGgGaAloD0MIVvMckS9ucUCUhpRSlGgVS5VoFkdAwgnfschkiHV9lChoBmgJaA9DCAXhCihUxXJAlIaUUpRoFUuYaBZHQMIJ5g5imVJ1fZQoaAZoCWgPQwj6l6QyxTtxQJSGlFKUaBVLvWgWR0DCCfBEWqLkdX2UKGgGaAloD0MI0GBT51E2Y0CUhpRSlGgVTegDaBZHQMIJ/J9Aood1fZQoaAZoCWgPQwgm4q3z73lzQJSGlFKUaBVLwGgWR0DCCgSESM99dX2UKGgGaAloD0MI56vkY3f3bkCUhpRSlGgVS5poFkdAwgoai0OVgXV9lChoBmgJaA9DCFZkdEASE3JAlIaUUpRoFUvyaBZHQMIKG0QCjlB1fZQoaAZoCWgPQwhMbD6uzcpxQJSGlFKUaBVLrWgWR0DCCiFXmvGIdX2UKGgGaAloD0MIsYf2sQLTb0CUhpRSlGgVS6RoFkdAwgoiNz8xbnV9lChoBmgJaA9DCNdrelCQrnRAlIaUUpRoFUveaBZHQMIKJ4yXUpd1fZQoaAZoCWgPQwh8YMd/wV9xQJSGlFKUaBVLrGgWR0DCCk8d5prUdX2UKGgGaAloD0MImBQfn5DxcUCUhpRSlGgVS6JoFkdAwgpPslb/wXV9lChoBmgJaA9DCBR3vMmvMXBAlIaUUpRoFUuiaBZHQMIKYAnMMZx1fZQoaAZoCWgPQwhFSN3OPsZwQJSGlFKUaBVLrmgWR0DCCmDtXxOMdX2UKGgGaAloD0MIB+qUR7c9ckCUhpRSlGgVS+VoFkdAwgphlGwzL3V9lChoBmgJaA9DCKZkOQmla3BAlIaUUpRoFUucaBZHQMIKZeQ2dd51fZQoaAZoCWgPQwjG+3H75cZzQJSGlFKUaBVLzWgWR0DCCnm5lOGkdX2UKGgGaAloD0MIWW3+X3VsS0CUhpRSlGgVS3toFkdAwgp89nscAHV9lChoBmgJaA9DCMHKoUU2ZnNAlIaUUpRoFUvraBZHQMIKiN0FKTV1fZQoaAZoCWgPQwhE96xr9AFwQJSGlFKUaBVLpGgWR0DCCpTFZPl/dX2UKGgGaAloD0MI6iPwhx+lckCUhpRSlGgVS6NoFkdAwgqU1NQCS3V9lChoBmgJaA9DCAoQBTPmoXNAlIaUUpRoFUvNaBZHQMIKlie/Yap1fZQoaAZoCWgPQwjLLEKxVYJzQJSGlFKUaBVLoWgWR0DCCpnWJ79idX2UKGgGaAloD0MICttPxriucUCUhpRSlGgVS6FoFkdAwgqexJNCaHV9lChoBmgJaA9DCCgqG9aU6XJAlIaUUpRoFUvmaBZHQMIKrrj5sTF1fZQoaAZoCWgPQwhy3ZTyWhdyQJSGlFKUaBVLlmgWR0DCCs8FwDNhdX2UKGgGaAloD0MI5e0IpwVkcUCUhpRSlGgVS61oFkdAwgrP0QK8c3V9lChoBmgJaA9DCCE6BI4ELk5AlIaUUpRoFUuXaBZHQMIK1JvHcUN1fZQoaAZoCWgPQwgLQnkfxx5zQJSGlFKUaBVLzGgWR0DCCua+SKWLdX2UKGgGaAloD0MINV1PdB00dECUhpRSlGgVS7doFkdAwgrmv7m+03V9lChoBmgJaA9DCJI9Qs2QQEtAlIaUUpRoFUt4aBZHQMIK7ScTakB1fZQoaAZoCWgPQwhNEHUfALdwQJSGlFKUaBVLpWgWR0DCCvSNXHR1dX2UKGgGaAloD0MIr1qZ8AvGckCUhpRSlGgVS9JoFkdAwgr5Zdv863V9lChoBmgJaA9DCBOaJJZUO3JAlIaUUpRoFUu+aBZHQMILAkl/pdN1fZQoaAZoCWgPQwhBn8iTJFdwQJSGlFKUaBVLpGgWR0DCCwmKjzqbdX2UKGgGaAloD0MI3WCow0qjcECUhpRSlGgVS65oFkdAwgsRGR3eN3V9lChoBmgJaA9DCCxmhLdHZ3JAlIaUUpRoFUvBaBZHQMILI1nVXmx1fZQoaAZoCWgPQwj5LxAECJ9wQJSGlFKUaBVLo2gWR0DCCyQJ1JUYdX2UKGgGaAloD0MIdXRcjazJckCUhpRSlGgVS79oFkdAwgsnkwvg33V9lChoBmgJaA9DCFK69C9JGXNAlIaUUpRoFUvjaBZHQMILK/pD/l11fZQoaAZoCWgPQwhIjJ5baFNiQJSGlFKUaBVN6ANoFkdAwgtKwcHW0HV9lChoBmgJaA9DCCL/zCC+V3BAlIaUUpRoFUuQaBZHQMILTAy2x6h1fZQoaAZoCWgPQwhW8rG7gDlwQJSGlFKUaBVLq2gWR0DCC04F1SwXdX2UKGgGaAloD0MINjy9UtbScUCUhpRSlGgVS8BoFkdAwgtWUyHmBHV9lChoBmgJaA9DCKj91k7UjnFAlIaUUpRoFUumaBZHQMILWgMlTm51fZQoaAZoCWgPQwhNFCF1e0FxQJSGlFKUaBVL0WgWR0DCC2d/+bVjdX2UKGgGaAloD0MIE2OZfkmac0CUhpRSlGgVS6NoFkdAwgtzmNBF/nV9lChoBmgJaA9DCIe/JmtUeXNAlIaUUpRoFUu8aBZHQMILealchTx1fZQoaAZoCWgPQwi1wvS9hlZ0QJSGlFKUaBVLs2gWR0DCC3vnIQvpdX2UKGgGaAloD0MIZoUi3Q95cUCUhpRSlGgVS7VoFkdAwguRZ26kI3V9lChoBmgJaA9DCMPTK2UZJnJAlIaUUpRoFUu0aBZHQMILm0Gu9vl1fZQoaAZoCWgPQwjpEDgS6PtvQJSGlFKUaBVLnGgWR0DCC6gEfT1DdX2UKGgGaAloD0MIkQn4NZIUQ0CUhpRSlGgVS6doFkdAwguxuwX67HV9lChoBmgJaA9DCIGyKVd4EHFAlIaUUpRoFUuuaBZHQMILvgwoLG91fZQoaAZoCWgPQwhY/nxb8C9xQJSGlFKUaBVLhWgWR0DCC8VNL128dWUu"
|
77 |
},
|
78 |
"ep_success_buffer": {
|
79 |
":type:": "<class 'collections.deque'>",
|
80 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
81 |
},
|
82 |
+
"_n_updates": 920,
|
83 |
"n_steps": 1024,
|
84 |
+
"gamma": 0.99,
|
85 |
+
"gae_lambda": 0.97,
|
86 |
"ent_coef": 0.01,
|
87 |
"vf_coef": 0.5,
|
88 |
"max_grad_norm": 0.5,
|
89 |
+
"batch_size": 32,
|
90 |
+
"n_epochs": 10,
|
91 |
"clip_range": {
|
92 |
":type:": "<class 'function'>",
|
93 |
+
":serialized:": "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"
|
94 |
},
|
95 |
"clip_range_vf": null,
|
96 |
"normalize_advantage": true,
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0668273f1e4acd8527f64281c2ded87c78d4959c6ff67a70a7a94b0d534fc575
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c12fbc875d04c8cf49a60b08ae14959eb156ffc29d108a97108c0542125f7136
|
3 |
+
size 43265
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -2,6 +2,6 @@
|
|
2 |
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
- PyTorch: 1.13.1+cu116
|
5 |
-
- GPU Enabled:
|
6 |
- Numpy: 1.22.4
|
7 |
- Gym: 0.21.0
|
|
|
2 |
- Python: 3.8.10
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: False
|
6 |
- Numpy: 1.22.4
|
7 |
- Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 281.0268009322872, "std_reward": 15.985919571177151, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-04T22:36:20.389991"}
|