Upload PPO LunarLander-v2 trained agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO-test
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -1269.17 +/- 691.43
+      name: mean_reward
+      verified: false
+---
+
+# **PPO-test** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO-test** 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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fb10ab20820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb10ab208b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb10ab20940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb10ab209d0>", "_build": "<function ActorCriticPolicy._build at 0x7fb10ab20a60>", "forward": "<function ActorCriticPolicy.forward at 0x7fb10ab20af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb10ab20b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb10ab20c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb10ab20ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb10ab20d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb10ab20dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb10ab20e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb10b448380>"}, "verbose": 3, "policy_kwargs": {}, "num_timesteps": 5041, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709274137750789628, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADN9Z73x8rA/NxmSvpUtN74or1+8mxfMvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.97952, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 16, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7894f83c247dcf50bebe45890d22c5829441c80f43cb3cf2e7c993dfc82e5e
+size 145521

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/data

@@ -0,0 +1,99 @@
+{
+    "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fb10ab20820>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb10ab208b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb10ab20940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb10ab209d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb10ab20a60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb10ab20af0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb10ab20b80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb10ab20c10>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb10ab20ca0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb10ab20d30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb10ab20dc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb10ab20e50>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb10b448380>"
+    },
+    "verbose": 3,
+    "policy_kwargs": {},
+    "num_timesteps": 5041,
+    "_total_timesteps": 200000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1709274137750789628,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADN9Z73x8rA/NxmSvpUtN74or1+8mxfMvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.97952,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVmgYAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwGvN0pEx7AuMAWyUS5GMAXSUR0ARm3mV7hNudX2UKGgGR8BSL/qHGjsVaAdLRWgIR0AR5tk4FRpDdX2UKGgGR8B4oJkhA4XGaAdLYWgIR0ASSjKxLTQWdX2UKGgGR8BirlrdnCfpaAdLT2gIR0ASmJXQtz0ZdX2UKGgGR8B41BeyAxzraAdLh2gIR0ATHtZ3cHnmdX2UKGgGR8B4bPmr8zhxaAdLZmgIR0ATfPIGQjlgdX2UKGgGR8BSW6CYkVvdaAdLQ2gIR0ATunCO3lS1dX2UKGgGR8Be0kWdmQKbaAdLP2gIR0AT9ie/Yao/dX2UKGgGR8Bne4JZ4fOlaAdLcGgIR0AUZRIjGDL9dX2UKGgGR8BdTCA6Mir1aAdLUWgIR0AUu5c1O0swdX2UKGgGR0AF6RdQfp2VaAdLaWgIR0AWQnYxtYSydX2UKGgGR8BYoERSP2f1aAdLRmgIR0AWgZl4C6pYdX2UKGgGR8B5Gff642CNaAdLYGgIR0AW1zMibDuSdX2UKGgGR8B3gVTn7pFDaAdLcWgIR0AXQSmIj4YadX2UKGgGR8A8PYdhiLEUaAdLSWgIR0AXg8nuy/sWdX2UKGgGR0A3Dzollbu/aAdLbGgIR0AX43qAz544dX2UKGgGR8BhMZzBAOawaAdLQ2gIR0AYHsgMc6vJdX2UKGgGR8BaaLNOdoWYaAdLRWgIR0AYX3K0UoKEdX2UKGgGR8BwkYvSMLncaAdLbGgIR0AYz8DSw4bTdX2UKGgGR8Bwfzd56dDqaAdLa2gIR0AZLB7/n4fwdX2UKGgGR8BYWxBE8aGYaAdLV2gIR0AZeq2jO9nLdX2UKGgGR8BoaAqbz9S/aAdLSGgIR0AZuHGjsUqQdX2UKGgGR8BsfuU6gdwOaAdLZWgIR0AbCSs8xKxtdX2UKGgGR8BmVH0ulGgBaAdLPWgIR0AbRLOAy2x6dX2UKGgGR8BCkxri2lVMaAdLS2gIR0AbiAVfu1F6dX2UKGgGR8BnzRLf1pTNaAdLbmgIR0Ab7jfek56udX2UKGgGR8BgMyPQv6CUaAdLWGgIR0AcPYxtYSxrdX2UKGgGR8BYMIjW07bMaAdLY2gIR0AclKHwgDA8dX2UKGgGR8BaKZuEVWS2aAdLVGgIR0Ac6cFyJbdKdX2UKGgGR8BkewQBgeA/aAdLXGgIR0AdOqaPS2H+dX2UKGgGR8BtzFUp/gBLaAdLV2gIR0AdjMlkYoAodX2UKGgGR8B1kKb3Gn4xaAdLXGgIR0Ad3jHXEqDsdX2UKGgGR8BlEEpobn5jaAdLf2gIR0AeU4uK4x1xdX2UKGgGR8BvOd4qwyIpaAdLXmgIR0AfoyEcsDnvdX2UKGgGR8BocSN2ki2VaAdLaGgIR0Af/jQzDXOGdX2UKGgGR8BvGYgmqo60aAdLbWgIR0AgMI42jwhGdX2UKGgGR8BbnOu7pV0caAdLTGgIR0AgUscQyylfdX2UKGgGR8BYGlyR0U48aAdLh2gIR0Agk8cMmWt2dX2UKGgGR8BhEBtFa0QcaAdLT2gIR0Agt5O8CgbqdX2UKGgGR8BXEyTQmeDnaAdLV2gIR0Ag3fzjFQ2udX2UKGgGR8BZAx0+1SflaAdLSGgIR0Ag/Y02tMfzdX2UKGgGR8Bm9szEaVD8aAdLR2gIR0AhHi/fwZwXdX2UKGgGR8BTDQosqaw2aAdLQmgIR0AhPA2ycCo1dX2UKGgGR8BoQGtW+49YaAdLT2gIR0AhXtXxOLzgdX2UKGgGR8BjwnYxtYSyaAdLcmgIR0AiEZAIIF/ydX2UKGgGR8BW5NAkcCHRaAdLQ2gIR0AiMEIw/PgOdX2UKGgGR8Bs3u4gA6uGaAdLXmgIR0AiWcPvrnkldX2UKGgGR8B/R0Bltj0+aAdLamgIR0AikP1ct5D7dX2UKGgGR8BolFJ6IFeOaAdLT2gIR0AitHBk7OmjdX2UKGgGR8Be67WiDdxiaAdLRmgIR0Ai29rXUYsNdX2UKGgGR8BWeFO9FnZkaAdLUGgIR0AjAbsF+uvEdX2UKGgGR8BZqcFUyYXwaAdLXGgIR0AjKyRjjJdTdX2UKGgGR8Bw97Ck43m3aAdLaGgIR0AjXFBppN9IdX2UKGgGR8BT/lFH8TBZaAdLd2gIR0Ajq81XNke7dX2UKGgGR8BY9kQXhwVCaAdLVWgIR0Aj6NwR5C4SdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 16,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": "Generator(PCG64)"
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVpAEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJRoG4wUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoJooQYeo9uR5/0Uogj47SHUahLYwDaW5jlIoRD0oSVfwZgNXoEtxLrE992gB1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpSKBQfuLKgAdWJ1Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d9bfc77d0b0d7756e10e6f5cc98c1f39752f00c432171fd0dc1d54427ef75f
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab4dc98a8c38b79cf25b72f074379cc8bcecd70a65bc8acf951fbed6b41d692
+size 43634

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: False
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -1269.1730925638228, "std_reward": 691.4339576521196, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-01T06:23:28.350144"}