Upload PPO LunarLander-v2-1M model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.19 +/- 28.27
+      value: 270.66 +/- 20.63
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-1M.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ffa06e72f5b9f092d098887fe202127ea9f3fc2389ae8b7706c0a1baad2707
+size 147170

ppo-LunarLander-v2-1M/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-LunarLander-v2-1M/data

@@ -0,0 +1,94 @@
+{
+    "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 0x7ff8851d7e50>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff8851d7ee0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff8851d7f70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff8851de040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff8851de0d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff8851de160>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff8851de1f0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff8851de280>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff8851de310>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff8851de3a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff8851de430>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7ff8851d9330>"
+    },
+    "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,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1671721992456136260,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAANPII77tsIA/g3zTvSd6DL+NTFK+5KzFvQAAAAAAAAAAzUJJvLSXsbwNKq08oXx/PEO0Ub298te9AACAPwAAgD/meRG9q+KsPw0g1L6lndq+JNJeu87sAL4AAAAAAAAAAM0NB71ESyY/Et3ZOdZj875acHu92kDhvAAAAAAAAAAAM8/5PAODTT0d4369J4h8vmK3V70SwbC8AAAAAAAAAAAa7R+9REPIPR7pnD4LFYK+M/5qPn2pH70AAAAAAAAAAM2wiLuu4Yy6+giXOlqAdzW4Bka7dlSvuQAAgD8AAIA/zSenPK53ybrqzYO8qY+XPKoCR7x1B4M9AACAPwAAgD8A/4A8H4+MuyovKjyHuCs80FzAPNBjF70AAIA/AACAP5rdlzzULW0+Fz0CPVCydb4qLgI7f4GiPAAAAAAAAAAAGmlgPcMxXrrDSeU6CjdNNkdiQTvaZgS6AACAPwAAgD+ag3W9tLnzPZNSzz3Hb1u+Hb3JvGXfA70AAAAAAAAAAI0yQj6+asA/QxEkPzCXRb7pRJs8viyEPgAAAAAAAAAAZkbOO6aVtD+FOSM/4NaWuxbM7rss5BO+AAAAAAAAAAAm8c89Ut+BPyA+6D2AFeO+OsyMPm2mtjsAAAAAAAAAADOE4DzsqIy7RZmJu6sslTwXnts8mi9+vQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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
+}

ppo-LunarLander-v2-1M/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a895c5ce6e0ba7617045d55f7a3a601cce1b90741960cee9579de014e90b3a
+size 87929

ppo-LunarLander-v2-1M/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cd5b1b5e28aaa0c1f731980d4f0b18538747e9c157b518c1cf5240ac7dd91b
+size 43201

ppo-LunarLander-v2-1M/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2-1M/system_info.txt

@@ -0,0 +1,7 @@
+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": 265.1911167302251, "std_reward": 28.273382690571925, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T15:34:15.354699"}
+{"mean_reward": 270.65627075963476, "std_reward": 20.62936787457723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T15:44:35.621814"}