Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 291.89 +/- 23.59
+      value: 285.90 +/- 22.92
       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 0x7f6e3ec33640>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6e3ec336d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6e3ec33760>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6e3ec337f0>", "_build": "<function ActorCriticPolicy._build at 0x7f6e3ec33880>", "forward": "<function ActorCriticPolicy.forward at 0x7f6e3ec33910>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6e3ec339a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6e3ec33a30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6e3ec33ac0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6e3ec33b50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6e3ec33be0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6e3ec2b8c0>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670523399047978083, "learning_rate": 0.0005, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2716, "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-5.15.74.2-microsoft-standard-WSL2-x86_64-with-glibc2.35 #1 SMP Wed Nov 2 19:50:29 UTC 2022", "Python": "3.10.6", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7f4c1dfc7640>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4c1dfc76d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4c1dfc7760>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4c1dfc77f0>", "_build": "<function ActorCriticPolicy._build at 0x7f4c1dfc7880>", "forward": "<function ActorCriticPolicy.forward at 0x7f4c1dfc7910>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4c1dfc79a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4c1dfc7a30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4c1dfc7ac0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4c1dfc7b50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4c1dfc7be0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f4c1dfbfec0>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670523399047978083, "learning_rate": 0.0005, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2716, "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:": "gAWV2wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMVC9ob21lL3l1Y2ppbi9neW0vdmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVC9ob21lL3l1Y2ppbi9neW0vdmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.74.2-microsoft-standard-WSL2-x86_64-with-glibc2.35 #1 SMP Wed Nov 2 19:50:29 UTC 2022", "Python": "3.10.6", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fdbab2caf729f1b03d7c8b3c4c82238a52eac6d9fcd4178817f2ef6d9b8100
+oid sha256:1f58131ab05ed9af82959c85593a70865c64f8c5955dc79647c2aaaf0b0f3c3a
 size 146388

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 0x7f6e3ec33640>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6e3ec336d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6e3ec33760>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6e3ec337f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f6e3ec33880>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f6e3ec33910>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6e3ec339a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f6e3ec33a30>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6e3ec33ac0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6e3ec33b50>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6e3ec33be0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f4c1dfc7640>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4c1dfc76d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4c1dfc7760>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4c1dfc77f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f4c1dfc7880>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f4c1dfc7910>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4c1dfc79a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f4c1dfc7a30>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4c1dfc7ac0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4c1dfc7b50>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4c1dfc7be0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f6e3ec2b8c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f4c1dfbfec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 291.89381119999996, "std_reward": 23.592860348379762, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T22:46:58.361624"}
+{"mean_reward": 285.9043851, "std_reward": 22.924586624231143, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-09T10:23:36.912676"}