Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -530.12 +/- 132.48
+      value: 246.61 +/- 25.03
       name: mean_reward
       verified: false
 ---

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 0x7fc6694be3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc6694be430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc6694be4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc6694be550>", "_build": "<function ActorCriticPolicy._build at 0x7fc6694be5e0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc6694be670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc6694be700>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc6694be790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc6694be820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc6694be8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc6694be940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc6694c0090>"}, "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": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 0x7f86708e35e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f86708e3670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f86708e3700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f86708e3790>", "_build": "<function ActorCriticPolicy._build at 0x7f86708e3820>", "forward": "<function ActorCriticPolicy.forward at 0x7f86708e38b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f86708e3940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f86708e39d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f86708e3a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f86708e3af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f86708e3b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f86708dade0>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670447363571418581, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAMZ9Ij7f2Es/ulGJPLaVZr5eMWg9DRIKPQAAAAAAAAAAZsUGPp5GhD2tHeC9peAkvqV9jbx9jBK9AAAAAAAAAABGADS+DkWcvH56a71EGz888i8NPv91F70AAIA/AACAP2DhHr6UX5G8whMZPlfOq73uRgA+xRuKPgAAgD8AAIA/2v/mPTSI/D4+vxK+HEJYviuFGr2u7dQ7AAAAAAAAAACTyTG+yM+ZPk5ERj1mUZq+ADS6vXnOAj4AAAAAAAAAANp41D0pkCa6ceeutzwNnLJVV5i6E3PQNgAAAAAAAIA/aOqCvmchN73OGSG78w75uZrWnj4QmFw6AACAPwAAgD/mD0K9XEdSukafFzvudUo3PMoLuxObAboAAIA/AACAP0DFLr5EMH0/IgFuvjpvxr5O+lW+q0gKPQAAAAAAAAAAM/RbPdKJoLtBDKO7M96gPPPJ57yeJYg9AACAPwAAgD9Ntt49KXA6umLT4rrzSr+1JPgoOCkOBDoAAAAAAACAP0CQtL32GHi6gzBtOUtbCLbvjOi6nJMCtQAAAAAAAIA/zTxtPFapiz56S4W8metxvuZWGL2Nh2A8AAAAAAAAAADNkyE9Y6SLPq75x72ySmS+XMMYPEfuKDsAAAAAAAAAAE0Kvj2ufYS6/o4sO5qC6LQiqPE5H7FHugAAAAAAAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": 248, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c622568d2e168caea11515d59af54944d95dc728e736da8a25fe6659408836f7
-size 52863
+oid sha256:4057303f621fb2ba0f3fbcfc692229cb982d9a561e383477c4687421647c1e0a
+size 147342

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 0x7fc6694be3a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc6694be430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc6694be4c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc6694be550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc6694be5e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc6694be670>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc6694be700>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc6694be790>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc6694be820>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc6694be8b0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc6694be940>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f86708e35e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f86708e3670>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f86708e3700>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f86708e3790>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f86708e3820>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f86708e38b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f86708e3940>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f86708e39d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f86708e3a60>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f86708e3af0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f86708e3b80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fc6694c0090>"
+        "_abc_impl": "<_abc_data object at 0x7f86708dade0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -42,28 +42,40 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1670447363571418581,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
-    "_last_obs": null,
-    "_last_episode_starts": null,
+    "_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": 1,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "_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": 248,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:866b216e0814e36ee8bb0d58a14c4798157410a20db9ab2ff5376bb871fc7b5d
+size 88057

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c309e6e1f1c62c6e840c811eb7431c15736917f3b76c880794e09cef95ae87
+oid sha256:dbacc0094bcbc19c56ac07d44edbba195930821740cd78c0f2269b7ef569a8eb
 size 43201

results.json

@@ -1 +1 @@
-{"mean_reward": -530.1237776689231, "std_reward": 132.4837462952446, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T21:02:27.538017"}
+{"mean_reward": 246.6096256958052, "std_reward": 25.029669966937853, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T21:41:49.331475"}