Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -664.15 +/- 207.29
+      value: 276.14 +/- 13.50
       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 0x7f7fec222ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7fec222f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7fec223010>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7fec2230a0>", "_build": "<function ActorCriticPolicy._build at 0x7f7fec223130>", "forward": "<function ActorCriticPolicy.forward at 0x7f7fec2231c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7fec223250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7fec2232e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7fec223370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7fec223400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7fec223490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7fec223520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f7fec21adc0>"}, "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-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.6", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "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 0x7fd87e0afa30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd87e0afac0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd87e0afb50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd87e0afbe0>", "_build": "<function ActorCriticPolicy._build at 0x7fd87e0afc70>", "forward": "<function ActorCriticPolicy.forward at 0x7fd87e0afd00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd87e0afd90>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd87e0afe20>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd87e0afeb0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd87e0aff40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd87e0c4040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd87e0c40d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd87e4ca8c0>"}, "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": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678715753861954784, "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.6", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7497f8d3ff9922fe937ba5d618ba763b6a7ab7ecc5a9e926df8c19978c8a732e
-size 53415
+oid sha256:d3ca22a436b5f7084542f442b5c94265dcc19e82426ee760a66f09d1f0a10c16
+size 147706

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 0x7f7fec222ef0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7fec222f80>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7fec223010>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7fec2230a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f7fec223130>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f7fec2231c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7fec223250>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7fec2232e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f7fec223370>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7fec223400>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7fec223490>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7fec223520>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fd87e0afa30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd87e0afac0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd87e0afb50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd87e0afbe0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fd87e0afc70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fd87e0afd00>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd87e0afd90>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd87e0afe20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fd87e0afeb0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd87e0aff40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd87e0c4040>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd87e0c40d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f7fec21adc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fd87e4ca8c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -43,28 +43,40 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1678715753861954784,
     "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": -0.007616000000000067,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 492,
     "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 sha256:934ff660564818aa953aafaa5f7299e10f9370c24a456b468af89362b1cb8462
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e1a81ac96d932b40eed3853bc689a32b5aea6100ddc5033f79b3c2be47d302
+oid sha256:421eba679ab3b317cfe3837fe2d7d7c88e7ef9fec0e7ab2864478dc2630355e4
 size 43393

results.json

@@ -1 +1 @@
-{"mean_reward": -664.1496818896383, "std_reward": 207.2882499730764, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-13T14:48:56.172007"}
+{"mean_reward": 276.1405015306784, "std_reward": 13.50247440232986, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-13T15:41:20.401777"}