First commit. 1E6 iterations

Lunar_Lander_1E6.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7e735452b8c5917d2578846cc24eb7f60d23f21a691d17661b67092dd08f79
-size 52863
+oid sha256:ebab355ea3f489e74f4613d4192eae1c3d6a680d6e0d9f13e2e8f620680a60a6
+size 147192

Lunar_Lander_1E6/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 0x7f2538102ca0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2538102d30>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2538102dc0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2538102e50>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f2538102ee0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f2538102f70>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2538106040>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f25381060d0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2538106160>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f25381061f0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2538106280>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7efc7869cca0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efc7869cd30>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efc7869cdc0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efc7869ce50>",
+        "_build": "<function ActorCriticPolicy._build at 0x7efc7869cee0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7efc7869cf70>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efc786a0040>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7efc786a00d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efc786a0160>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efc786a01f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efc786a0280>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f25380ff4b0>"
+        "_abc_impl": "<_abc_data object at 0x7efc786984b0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -42,28 +42,40 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000.0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1671355732200058246,
     "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": 248,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

Lunar_Lander_1E6/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:d5b6c9a55b4a15998c8594ae588cb8e9521eafd269f634d78d1450a9e0f31ebb
+size 87929

Lunar_Lander_1E6/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41eaeaaa0d3e2f17cf411b61d4c2319ac9588002664d867fdc3bce938112358
+oid sha256:1ff478af2541bf78b7aac9d1639db5168026af2c7e63c238aad0de4b9f6bce04
 size 43201

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -447.52 +/- 288.23
+      value: 239.00 +/- 67.42
       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 0x7f2538102ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2538102d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2538102dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2538102e50>", "_build": "<function ActorCriticPolicy._build at 0x7f2538102ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2538102f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2538106040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f25381060d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2538106160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f25381061f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2538106280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f25380ff4b0>"}, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7efc7869cca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efc7869cd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efc7869cdc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efc7869ce50>", "_build": "<function ActorCriticPolicy._build at 0x7efc7869cee0>", "forward": "<function ActorCriticPolicy.forward at 0x7efc7869cf70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efc786a0040>", "_predict": "<function ActorCriticPolicy._predict at 0x7efc786a00d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efc786a0160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efc786a01f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efc786a0280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7efc786984b0>"}, "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": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671355732200058246, "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": 248, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -447.5205484837294, "std_reward": 288.23082652434346, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T09:15:31.031730"}
+{"mean_reward": 239.0026974112067, "std_reward": 67.41601425894416, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T10:01:53.017892"}