dummy trial

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -583.58 +/- 135.90
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 0x7f21a7225680>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f21a7225710>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f21a72257a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f21a7225830>", "_build": "<function ActorCriticPolicy._build at 0x7f21a72258c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f21a7225950>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f21a72259e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f21a7225a70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f21a7225b00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f21a7225b90>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f21a7225c20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f21a71f9390>"}, "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:": "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", "n": 4, "_shape": [], "dtype": "int64", "_np_random": "RandomState(MT19937)"}, "n_envs": 1, "num_timesteps": 1024, "_total_timesteps": 50, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1667747520945718669, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAMBKSL44nsM/y+EdvwqEHb6QjAk/M1euPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -19.48, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8, "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-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef8f1250e207fac8a8b14fe376edb4710a4b71f2c29bffb9e12323b06514cfb
+size 145252

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/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 0x7f21a7225680>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f21a7225710>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f21a72257a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f21a7225830>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f21a72258c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f21a7225950>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f21a72259e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f21a7225a70>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f21a7225b00>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f21a7225b90>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f21a7225c20>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f21a71f9390>"
+    },
+    "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:": "gAWVLgsAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUaBOMBXN0YXRllH2UKIwDa2V5lIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolsAJAAAAAAAATYZpSjclNbA5hJl46EK63Sq6Yo4OMgegV6K98PuuO8vORJZ5lbeUTmyNvK/OYlgp4J7T5AFbBGpXcVroUJO8WIaAHxE8487C6cTPUPZX2UTdFD3I9FH7v8e6M3DwZV+TULHntiz3w+i8DGqRMEyslmJYPQtevOHKdSAW8+niC7DZbPqWXifGyNNkMoGc9VJQWonz7V2Ptc6m0iww07QpL3GpQdDxAYrQlXEkcWGAw7t0DaRUj+HPlbmeMrHggpHk0/+vl5qDVipQflf3hrABqVjpEOmt0XBxPjHb5tM9iLCC7KTwB4aqJL9foHz99TB5boLza3TyqC3rKWV4njGZskg3eqGHxCHyfCJpmhV12iVQ9taRHUGgpsxx5VKO4edkuRV5+EkZTFrUrkSbxfHbfXgZ12MBjIoM20O5RH9fw9gijmGGcFWdZIYgL42YtDY1Woyle21OfTbvQU2RjhCTl9Flgu0YEFFtD8eH/iQigWUrzyoKzbbON4GYKvvjCWbCe/HNGXSQQKQ7amEEDyIQuqJEEGduFVTkijvbkUPKU2lK5rIe613IcKlg4tTdKZZ/uZcD9dSsNjrgme2oC8E+bgO5+DrIl4bw7E7OcmpLM9h6y5lyqTDAPdAEOTkPNETuMDiZc1sV2fTUgDmqXZd0cQmlhViMx6q6gfIiTHScALlZEltRZJZZ7qcmonrV+cVH6UmxAzSLidji+Q2yV2rGxFjQS00M4fpvCNqMVPy66HIa76YceHZDfj3NoFAubXTZpUbKDuwP6jH639O2NeqSq2qGuxGo2iLok4XcNOs/39TccXICGhTL/RnXCd1cvaOKk3i6HvlhjKB+Rgq2ewrm6rsWfk9SS1W689yqRLyRjprC2Sqb9PggAILp/uFaIILYiwSk5zGrMRFcnuTEM08by3oEth0LxfwhEoQLXjTY557Hsw9RfAftJ2w0epMOkG7DVTXHXw9suVXW6GFTKyKs+wzA7BwOAKfof5fMDWbi7HWo8aLZE9cNZQf0otLdJ8o/M/SuWz+AHdwZ9Uf9R1yJ03ZRiRg/oGOeE5FT9Q14hRPth7NS7hwwmajqsiHjfwmrwLYfgnwC8lCNbp+X2u6xlEKe0lVQQnsupQ7xludP1sQG9uJRXXiA2JoZJTAuZA1zO6PrEfOE8c9oJZqIZZGyqFnU9rIH/jP/yqFybffujp9ZEjrRW6Zf7ihlHd7LAvpZIPjb1Fzh6pOYoN0QItFZbEadjANHaZYnHiO/aOfCtFSvNM/p1rs4tpzo3glvyWYw1qtpTOE7RKF+4LjjlHfLLAk2B337pec9VCrhyAadn5rbFsYfKZXKg32OX6Nxy8icH8zv9D6t+HRqvvqYIToJbHytayxJl3Phrlw5i5Uh8Z7xBdoqzBixCxy3UKVm1Vp4+R5+M4EzwhBfUEyyIxbLkFDPH5uf6+lnD+t0MJPfP4d/7UlVnzpI6RhWG/crVJmLTSOiUy73ciIP5ZMEBGasW7v0V34OcrT/DyrUNAHAHiCZw4ICNKXuiZJPzCCsOVaoAhmBJ8BJGPtWuyVekQaqc2xKEvuabThu2UZ8ReIVjx+T1DjEffQlZ5MBMNk5XrbGwkXU05+1prwYF6KlN3Y4ZtcsIsoPbmmI7ZmeanRjkZxqvFL520ZMMcgm7DaUekw10tkzetz+jO5NsD3e0pC0oFeQBRELPApDUV/eYMGRrciRgO/7M7PONtz55ogwhKerDzCom2tF3ifLIp/DIoDKUsLqe753Ai9EtH82RQBluVsZ6mA4WMOqQLv+mswv8y3hmqb6ZOF2hhGXIHuCz2BECU1hXCi33UtEEMCLf33ufTVy6Yqqi43lXP+2VwHcQitPgJxH65TGhlAA+cA0CDR7hFq5NlxI5djncYM13SIuO7xHGVHgqiQQKW+HwfCX83GrmpzwdVvl/BTnH1a8vRcmh03PNrforsgOMk0n9W/0uoHbc2tqzInpz6NS4C+IJHrebfu+yZZ7PU9yiYvhQuS3qTV0Suohnd1VmiI5lS1H7o99MTXP0VIv4NHhh9ZXo2grWIDjUQb+k64TqINp+4ssy2GVwJkX692C7Aqkggwz0N7hpo2brJ5L+not6IjQQ9YAlv3527lafL1pID7NypyY2hKlQTWhW7XEMPWny+a1XVVjxcZliO+O0R6MtbIMvCyZRYHJchKmuIjukWYakD3L24Txy6PadvHpn/qTk+lQKW437ieOVuD6tSOu5hSf+myL0nzovPIUFUIKbxPnngRYIF4IrK7P/2v9pysalCAP6I9kd1KatSIq9bT2mhbgJG4YH9JcXE45MTgrUFrs2EaJJNrk53DDaX8N4Nwz6PbQu0HMagwa8uGXtSC+T9RP1lE4fSnU7WStnAdKTRAGy1cCyPEDPg61CmnkVZtzmn/qOKfS+YzT5I5ZJQsAlR6iybuVSMgyCh2bPwzOYR6J+ZX9mvoRCp8x9tNMT435CwY6Vg9ssLbbAdzgggBPdxUf6+4W1q5f//srmrTKAzT07ESd3ftutlEkFsBTh6GOiSrV/ayYvnGDu0nIA+fySiK7DPsVkkC94BKgYDMEvciM97P1PerlXY7WP2/FH+9lyyXJRa+sA+oFmScM+XU33AQzBWJlwsaVL5U9Q75HFYEFjSK2VmLu1ezkSlluQJm2F1VULW9VBSnDzg8CttuiFfdurmGeO/ruURXrq+6Wx6Azv+HrCwjxZ1nX7oNXNnUjP6RL8UPimJGFpKe21d4zczNPfXqHxlfy6rYFBAXROWzYGGsTY0RxoFefwak995tTsv+hRLApAJwFPw1kw4/UtTUbPx0QVWj2Ni6driezwjXuPtR6IodsusAmQFIufyc8L2E+4VaGrM4q2jMqahAUM/FxRUemOxUdB8EpiBVZjhuTibyYlrqmIkAFi01AB0rdHXku8NFRkr79NocoUcNat/Ilx/YaKpBmKQb7BXnBqsCZE2A5S4BxeV96daxCIdV5w5P6gQEXlNcDktakJ3hSpn4B7C6xlENm7YiBY1BJE14IlkLI3qrJNFtpKWwAeDJl1rlHM/MoaV/g+dZHrgc/mkiFlz7TTtdItz/BiLwrJkFSrEnXcbDoSJY7QDnZv2SgOoi2CnaBPLwhBDKp/HiM5ThbtbSAxUZuKHT1Mxj/AFzHGFo4ZlFgmGXAgQts5/4MYH16QwSScGnLugNHv4uSOQptdQMgRpdaei1BwC3WfYXu8QImIqgnrme0oDs/DKy3JrUlWL/8GP2ubEOiuKwH9uAQP+Kidq7x2kDH8RwRE6wIO04g/xKpW6hKww13UOvoq7LqVc2ooSj8OwBi4Xkno8ZvjsUnlGgJjAJ1NJSJiIeUUpQoSwNoDU5OTkr/////Sv////9LAHSUYk1wAoWUjAFDlHSUUpSMA3Bvc5RLFHWMCWhhc19nYXVzc5RLAIwFZ2F1c3OURwAAAAAAAAAAdWJ1Yi4=",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1024,
+    "_total_timesteps": 50,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1667747520945718669,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAMBKSL44nsM/y+EdvwqEHb6QjAk/M1euPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -19.48,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 8,
+    "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/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddb0979e168e4d562ab97817a6ebeb2422d5b7a061a862a6f92c8150b4b93e1
+size 87865

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b4cdd876355af3750d9d6c575bd0f656a8d76b6b2a0e19553a0d8e2dace572
+size 43201

ppo-LunarLander-v2/pytorch_variables.pth

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

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.7.15
+Stable-Baselines3: 1.6.2
+PyTorch: 1.12.1+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -583.583479506406, "std_reward": 135.90336463059305, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-06T15:16:09.843475"}