PPO LunarLander-v2 trained agent

PPO-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99733caebe2723bab486eab46d8089f4032febb17d07e0da26d220751b0368b7
-size 52895
+oid sha256:738564c3a05d16740d26126344fca2ebb27344ac499df704adc14180e2947c68
+size 146157

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 0x15b7bcee0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15b7bcf70>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15b7c2040>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15b7c20d0>",
-        "_build": "<function ActorCriticPolicy._build at 0x15b7c2160>",
-        "forward": "<function ActorCriticPolicy.forward at 0x15b7c21f0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15b7c2280>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x15b7c2310>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15b7c23a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15b7c2430>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x15b7c24c0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x12f697d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12f697dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12f697e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12f697ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x12f697f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x12f69e040>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12f69e0d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x12f69e160>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12f69e1f0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12f69e280>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x12f69e310>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x15b7bf1b0>"
+        "_abc_impl": "<_abc_data object at 0x12f6991b0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -42,28 +42,40 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1671423118782124000,
     "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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADP+uLwcvB89vbv+PGFRR74ungg8ZNcGvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
     "_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": -0.00044800000000000395,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 3908,
     "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 sha256:1843d3a7f2fb29da19c958857130f9decd4130a8c972e39c00b516d748999bf7
+size 87545

PPO-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54a12f51191fd195d8c03edfcc445808f67fd9bda33e5a5b1548eb88aa2a9b6
+oid sha256:e96dce66dfc26c166d965c16bb0c25ae815a7faf13d596b1455422755472a760
 size 43073

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -572.18 +/- 140.41
+      value: 244.54 +/- 59.15
       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 0x15b7bcee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15b7bcf70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15b7c2040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15b7c20d0>", "_build": "<function ActorCriticPolicy._build at 0x15b7c2160>", "forward": "<function ActorCriticPolicy.forward at 0x15b7c21f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15b7c2280>", "_predict": "<function ActorCriticPolicy._predict at 0x15b7c2310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15b7c23a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15b7c2430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x15b7c24c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x15b7bf1b0>"}, "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": 1, "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:": "gAWV+wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZC9vcHQvaG9tZWJyZXcvYW5hY29uZGEzL2VudnMvdG9yY2gtZ3B1L2xpYi9weXRob24zLjgvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGQvb3B0L2hvbWVicmV3L2FuYWNvbmRhMy9lbnZzL3RvcmNoLWdwdS9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.24.0", "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 0x12f697d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12f697dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12f697e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12f697ee0>", "_build": "<function ActorCriticPolicy._build at 0x12f697f70>", "forward": "<function ActorCriticPolicy.forward at 0x12f69e040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12f69e0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x12f69e160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12f69e1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12f69e280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x12f69e310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x12f6991b0>"}, "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": 1, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671423118782124000, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADP+uLwcvB89vbv+PGFRR74ungg8ZNcGvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "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": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.24.0", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -572.1812760421075, "std_reward": 140.4140525006824, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T19:57:58.121216"}
+{"mean_reward": 244.54147172110615, "std_reward": 59.15192598769222, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T20:20:57.184546"}