Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -496.19 +/- 112.39
+      value: 272.80 +/- 20.08
       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 0x7fb2584c10d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb2584c1160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb2584c11f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb2584c1280>", "_build": "<function ActorCriticPolicy._build at 0x7fb2584c1310>", "forward": "<function ActorCriticPolicy.forward at 0x7fb2584c13a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb2584c1430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb2584c14c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb2584c1550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb2584c15e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb2584c1670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb2584c1700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb2584bfa00>"}, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7fa425c7cf70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa425c7f040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa425c7f0d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa425c7f160>", "_build": "<function ActorCriticPolicy._build at 0x7fa425c7f1f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fa425c7f280>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa425c7f310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa425c7f3a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa425c7f430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa425c7f4c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa425c7f550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa425c7f5e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa425c7e740>"}, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678316201362844653, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e90c1d0f0b5a782e6638e2a726af64efe8f0f55e6bec7abad66ecd267d0352
-size 53074
+oid sha256:fcf2080238e085014ff207f9e5a63ed75e8b6e67d928f7f12004b064a2ee3141
+size 147345

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 0x7fb2584c10d0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb2584c1160>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb2584c11f0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb2584c1280>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fb2584c1310>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fb2584c13a0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb2584c1430>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb2584c14c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fb2584c1550>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb2584c15e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb2584c1670>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb2584c1700>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa425c7cf70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa425c7f040>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa425c7f0d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa425c7f160>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa425c7f1f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa425c7f280>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa425c7f310>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa425c7f3a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa425c7f430>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa425c7f4c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa425c7f550>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa425c7f5e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fb2584bfa00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa425c7e740>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -43,28 +43,40 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1507328,
+    "_total_timesteps": 1500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1678316201362844653,
     "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": -0.004885333333333408,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 368,
     "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 sha256:8a58833a1ac27028221bb6e8e7b03a42da9ec1daaa7c628c1dee5e06fde3ccd5
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed3ee2d17bc32df32ac1d73ff1406c653fdb39e0a0d275e9af4acce06d58954
+oid sha256:6dc6504e1089d0f653e44e46fdafac2a8702836c29fa67455c44172343fc2796
 size 43393

results.json

@@ -1 +1 @@
-{"mean_reward": -496.19040421172974, "std_reward": 112.39117232432345, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T22:12:07.600078"}
+{"mean_reward": 272.796600198637, "std_reward": 20.079786165893257, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T23:23:10.672156"}