Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 180.02 +/- 99.59
+      value: 203.14 +/- 77.37
       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 0x145e99750>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x145e997e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x145e99870>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x145e99900>", "_build": "<function ActorCriticPolicy._build at 0x145e99990>", "forward": "<function ActorCriticPolicy.forward at 0x145e99a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x145e99ab0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x145e99b40>", "_predict": "<function ActorCriticPolicy._predict at 0x145e99bd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x145e99c60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x145e99cf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x145e99d80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x145e96200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682879514803725000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-13.3.1-arm64-arm-64bit Darwin Kernel Version 22.4.0: Mon Mar  6 20:59:58 PST 2023; root:xnu-8796.101.5~3/RELEASE_ARM64_T6020", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0", "GPU Enabled": "False", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.28.1"}}
+{"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 0x16ba95ea0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16ba95f30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16ba95fc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16ba96050>", "_build": "<function ActorCriticPolicy._build at 0x16ba960e0>", "forward": "<function ActorCriticPolicy.forward at 0x16ba96170>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x16ba96200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16ba96290>", "_predict": "<function ActorCriticPolicy._predict at 0x16ba96320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16ba963b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16ba96440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x16ba964d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x16ba92340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682879514803725000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVMwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMgC9vcHQvaG9tZWJyZXcvQ2Fza3Jvb20vbWluaWNvbmRhL2Jhc2UvZW52cy9odWdnaW5nZmFjZS1kcmwtY291cnNlL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLhEMCBAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIyAL29wdC9ob21lYnJldy9DYXNrcm9vbS9taW5pY29uZGEvYmFzZS9lbnZzL2h1Z2dpbmdmYWNlLWRybC1jb3Vyc2UvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "system_info": {"OS": "macOS-13.3.1-arm64-arm-64bit Darwin Kernel Version 22.4.0: Mon Mar  6 20:59:58 PST 2023; root:xnu-8796.101.5~3/RELEASE_ARM64_T6020", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0", "GPU Enabled": "False", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.28.1"}}

ppo-llv2-rl-course.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be17e23801105ce27827f1921d4b76c60ee3dd5ead6ad78ef9eb5ba3bb0c58ee
+oid sha256:d19bb0526588a68039f3208967af12660edba4a0d1ce4e5c5149b4b976128511
 size 147299

ppo-llv2-rl-course/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 0x145e99750>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x145e997e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x145e99870>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x145e99900>",
-        "_build": "<function ActorCriticPolicy._build at 0x145e99990>",
-        "forward": "<function ActorCriticPolicy.forward at 0x145e99a20>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x145e99ab0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x145e99b40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x145e99bd0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x145e99c60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x145e99cf0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x145e99d80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x16ba95ea0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16ba95f30>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16ba95fc0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16ba96050>",
+        "_build": "<function ActorCriticPolicy._build at 0x16ba960e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x16ba96170>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x16ba96200>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16ba96290>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x16ba96320>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16ba963b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16ba96440>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x16ba964d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x145e96200>"
+        "_abc_impl": "<_abc._abc_data object at 0x16ba92340>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 180.02496508227154, "std_reward": 99.59128473516932, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-30T18:11:00.958328"}
+{"mean_reward": 203.13572676398508, "std_reward": 77.3720737379406, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-30T18:19:05.358193"}