Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -604.02 +/- 190.05
+      value: 269.26 +/- 19.81
       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 0x2824d81f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2824d8280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2824d8310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2824d83a0>", "_build": "<function ActorCriticPolicy._build at 0x2824d8430>", "forward": "<function ActorCriticPolicy.forward at 0x2824d84c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x2824d8550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2824d85e0>", "_predict": "<function ActorCriticPolicy._predict at 0x2824d8670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2824d8700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2824d8790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x2824d8820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2824c71c0>"}, "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": 2048, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "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 0x12bad5000>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12bad5090>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12bad5120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12bad51b0>", "_build": "<function ActorCriticPolicy._build at 0x12bad5240>", "forward": "<function ActorCriticPolicy.forward at 0x12bad52d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x12bad5360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12bad53f0>", "_predict": "<function ActorCriticPolicy._predict at 0x12bad5480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12bad5510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12bad55a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x12bad5630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x12bac76c0>"}, "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": 1678794003569639000, "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": 310, "n_steps": 2048, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "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 sha256:17b49c00ccefed041365b697bb28b88eb0f399422048f2a100d4a9b0d9b35ba7
-size 53204
+oid sha256:436c61bd3d2a0ddaea8cad5a70856ee3a23a9eb161d83e9081680d599c52e826
+size 147071

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 0x2824d81f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2824d8280>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2824d8310>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2824d83a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x2824d8430>",
-        "forward": "<function ActorCriticPolicy.forward at 0x2824d84c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x2824d8550>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2824d85e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x2824d8670>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2824d8700>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2824d8790>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x2824d8820>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x12bad5000>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12bad5090>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12bad5120>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12bad51b0>",
+        "_build": "<function ActorCriticPolicy._build at 0x12bad5240>",
+        "forward": "<function ActorCriticPolicy.forward at 0x12bad52d0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x12bad5360>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12bad53f0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x12bad5480>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12bad5510>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12bad55a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x12bad5630>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x2824c71c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x12bac76c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -43,28 +43,40 @@
         "_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": 1678794003569639000,
     "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": 310,
     "n_steps": 2048,
     "gamma": 0.99,
     "gae_lambda": 0.95,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:3b7afd4e02386610cfd0e4a3710ba5272de2c088dac34e9429726c6adca1e97a
+size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342cac2f9308429d70773d2af6baa5dd5b68a4f53a981edb23e7c3cfb1856153
+oid sha256:cb35b3f2b37c74c93d7e03ef770dabff653cc25791470e14dd1c6b0cec725f7c
 size 43265

results.json

@@ -1 +1 @@
-{"mean_reward": -604.0239802658558, "std_reward": 190.0451037819023, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-14T20:10:50.310350"}
+{"mean_reward": 269.25807026863595, "std_reward": 19.807838338978332, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-14T20:49:29.237550"}