Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -89.00 +/- 41.18
+      value: -829.34 +/- 341.30
       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 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 0x7eff0fe724c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff0fe72550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff0fe725e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff0fe72670>", "_build": "<function ActorCriticPolicy._build at 0x7eff0fe72700>", "forward": "<function ActorCriticPolicy.forward at 0x7eff0fe72790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff0fe72820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff0fe728b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7eff0fe72940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff0fe729d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff0fe72a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff0fe72af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7eff0fe6aa50>"}, "verbose": 0, "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": 1, "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": 0.99, "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-5.10.147+-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": "1.21.6", "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 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 0x7fcbe8646e50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcbe8646ee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcbe8646f70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcbe864a040>", "_build": "<function ActorCriticPolicy._build at 0x7fcbe864a0d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fcbe864a160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcbe864a1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcbe864a280>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcbe864a310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcbe864a3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcbe864a430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcbe864a4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcbe8642c60>"}, "verbose": 0, "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": 1, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677063851357816900, "learning_rate": 0.505988249401893, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABgzoL5azAhA8Epbv4XBkD/LQJ4+PYwkPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_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": 980, "n_steps": 1024, "gamma": 0.9317539296272632, "gae_lambda": 0.9182480658673623, "ent_coef": 0.04836019970542158, "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-5.10.147+-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": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3958bc2503999e418fde027561a0952e21e208f49faf36a043b6ccac560135d
-size 52940
+oid sha256:1d6742870aaa3bbeeced89689593b254e6bb3b829ddf735c32ab93279ea66a08
+size 146181

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7eff0fe724c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff0fe72550>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff0fe725e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff0fe72670>",
-        "_build": "<function ActorCriticPolicy._build at 0x7eff0fe72700>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7eff0fe72790>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff0fe72820>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff0fe728b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7eff0fe72940>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff0fe729d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff0fe72a60>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff0fe72af0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fcbe8646e50>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcbe8646ee0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcbe8646f70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcbe864a040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcbe864a0d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcbe864a160>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcbe864a1f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcbe864a280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcbe864a310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcbe864a3a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcbe864a430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcbe864a4c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7eff0fe6aa50>"
+        "_abc_impl": "<_abc_data object at 0x7fcbe8642c60>"
     },
     "verbose": 0,
     "policy_kwargs": {},
@@ -43,32 +43,44 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 100352,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
-    "learning_rate": 0.0003,
+    "start_time": 1677063851357816900,
+    "learning_rate": 0.505988249401893,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABgzoL5azAhA8Epbv4XBkD/LQJ4+PYwkPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
     },
-    "_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,
+    "_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": 980,
     "n_steps": 1024,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "gamma": 0.9317539296272632,
+    "gae_lambda": 0.9182480658673623,
+    "ent_coef": 0.04836019970542158,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:2f7e83ea2249f3e948f8a7797447d901e950931e6d1c3bc344fe6aca2b3286e3
+size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ba3babf10bd3835faef5229e21a948640f11e4dc5d113ac3ef4f95fd5e5773
+oid sha256:bff0271b509593d6b3aac753a3b2d7c57da3df48994f56cebb473b5294c2b78e
 size 43265

results.json

@@ -1 +1 @@
-{"mean_reward": -88.9957808105275, "std_reward": 41.1765105866572, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-20T11:31:49.497177"}
+{"mean_reward": -829.340426234249, "std_reward": 341.3020987535712, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-22T11:08:26.927740"}