Trained with 1000000 steps and HF's parameters

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 265.63 +/- 22.85
+      value: 263.26 +/- 18.38
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2-1000000-steps-hf.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2700e99ebdb1395d204319017730468b470a5292352aab0151f2cd251f4181e9
+size 144177

ppo-LunarLander-v2-1000000-steps-hf/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-LunarLander-v2-1000000-steps-hf/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 0x7fa70d43be50>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa70d43bee0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa70d43bf70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa70d3bd040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa70d3bd0d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa70d3bd160>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa70d3bd1f0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa70d3bd280>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa70d3bd310>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa70d3bd3a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa70d3bd430>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa70d3be180>"
+    },
+    "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": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1651846838.0863905,
+    "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
+}

ppo-LunarLander-v2-1000000-steps-hf/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfaefcad6162e53f437d597fa5e331a13f76222a5541adeb1caeca1c5abc7ce
+size 84829

ppo-LunarLander-v2-1000000-steps-hf/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affb307b51052cbe84b32fc677554789e9db5ee062a7fdf897fc3253caeaeadf
+size 43201

ppo-LunarLander-v2-1000000-steps-hf/pytorch_variables.pth

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

ppo-LunarLander-v2-1000000-steps-hf/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-109-generic-x86_64-with-glibc2.27 #123~18.04.1-Ubuntu SMP Fri Apr 8 09:48:52 UTC 2022
+Python: 3.9.6
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: True
+Numpy: 1.21.3
+Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6579b8636ff8d2638997ccc541368c421f7c3772f82bf8c1465d9299e32ac779
-size 234471
+oid sha256:196ea47d69f5863301845c0a43b5e058e3c6ceca40e7e69b7d7af998b276e684
+size 236916

results.json

@@ -1 +1 @@
-{"mean_reward": 265.6348964103681, "std_reward": 22.850509201466213, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T23:41:49.778132"}
+{"mean_reward": 263.2569365434525, "std_reward": 18.382460430274858, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T00:09:32.011925"}