First RL model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

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: 260.45 +/- 11.49
+      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 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 0x7fd467543380>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd467543420>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd4675434c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd467543560>", "_build": "<function ActorCriticPolicy._build at 0x7fd467543600>", "forward": "<function ActorCriticPolicy.forward at 0x7fd4675436a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd467543740>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd4675437e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd467543880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd467543920>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd4675439c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd467543a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd4676b9f00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1749766557301458531, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "gAWVugMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBEsDQySXAHQBAAAAAAAAAAAAAHwAZAGsAqYCAACrAgAAAAAAAAAAUwCUTkc/dHrhR64Ue4wScHJvZ3Jlc3NfcmVtYWluaW5nlIwNaW5pdGlhbF92YWx1ZZSGlIeUjBZzaW1wbGVfbGluZWFyX3NjaGVkdWxllIWUjBNwcm9ncmVzc19yZW1haW5pbmcxlIWUjB08aXB5dGhvbi1pbnB1dC0xNC00MDU1Njc3MzI4PpSMCDxsYW1iZGE+lIwIPGxhbWJkYT6USwdDI4AA1ThO0GJ18AAARgJLAvAAADlNAvEAADlNAvQAADlNAoAAlEMAlCkpdJRSlH2UKIwLX19wYWNrYWdlX1+UTowIX19uYW1lX1+UjAhfX21haW5fX5R1Tk5OdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHX2UfZQoaBqMCDxsYW1iZGE+lIwMX19xdWFsbmFtZV9flIwIPGxhbWJkYT6UjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgbjAdfX2RvY19flE6MC19fY2xvc3VyZV9flE6MF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lGgNaAIoaAcoSwJLAEsASwNLA0sDQzSXAHwAfAF6BQAAZAF6AAAAfQJ0AQAAAAAAAAAAAAB8AqYBAACrAQAAAAAAAAAAAQB8AlMAlE5HPxo24uscQy2GlIwFcHJpbnSUhZRoCWgKjAV2YWx1ZZSHlIwcPGlweXRob24taW5wdXQtMTMtNjI5ODk4MjY5PpSMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaA1LAUMhgADYDR+gLdENL7A20Qw5gEXdBAmIJYFMhEyATNgLEIBMlGgVKSl0lFKUaBhOTk50lFKUaB9oPH2UfZQoaBqMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaCOMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaCV9lChoCYwIYnVpbHRpbnOUjAVmbG9hdJSTlGgKaER1aCdOaChOaCloG2gqTmgrTmgsXZRoLn2UdYaUhlIwc3WGlIZSMC4="}, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "_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": 160, "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": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

my_first_rl_model.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94087a3b6f26214949bf6275ace44fb44af78ef761f08ae830cc4a7e6421461c
+size 149788

my_first_rl_model/_stable_baselines3_version

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

my_first_rl_model/data

@@ -0,0 +1,102 @@
+{
+    "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 0x7fd467543380>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd467543420>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd4675434c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd467543560>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fd467543600>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fd4675436a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd467543740>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd4675437e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fd467543880>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd467543920>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd4675439c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd467543a60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fd4676b9f00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 524288,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1749766557301458531,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.04857599999999995,
+    "_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": 160,
+    "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": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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:": "gAWVugMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBEsDQySXAHQBAAAAAAAAAAAAAHwAZAGsAqYCAACrAgAAAAAAAAAAUwCUTkc/dHrhR64Ue4wScHJvZ3Jlc3NfcmVtYWluaW5nlIwNaW5pdGlhbF92YWx1ZZSGlIeUjBZzaW1wbGVfbGluZWFyX3NjaGVkdWxllIWUjBNwcm9ncmVzc19yZW1haW5pbmcxlIWUjB08aXB5dGhvbi1pbnB1dC0xNC00MDU1Njc3MzI4PpSMCDxsYW1iZGE+lIwIPGxhbWJkYT6USwdDI4AA1ThO0GJ18AAARgJLAvAAADlNAvEAADlNAvQAADlNAoAAlEMAlCkpdJRSlH2UKIwLX19wYWNrYWdlX1+UTowIX19uYW1lX1+UjAhfX21haW5fX5R1Tk5OdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHX2UfZQoaBqMCDxsYW1iZGE+lIwMX19xdWFsbmFtZV9flIwIPGxhbWJkYT6UjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgbjAdfX2RvY19flE6MC19fY2xvc3VyZV9flE6MF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lGgNaAIoaAcoSwJLAEsASwNLA0sDQzSXAHwAfAF6BQAAZAF6AAAAfQJ0AQAAAAAAAAAAAAB8AqYBAACrAQAAAAAAAAAAAQB8AlMAlE5HPxo24uscQy2GlIwFcHJpbnSUhZRoCWgKjAV2YWx1ZZSHlIwcPGlweXRob24taW5wdXQtMTMtNjI5ODk4MjY5PpSMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaA1LAUMhgADYDR+gLdENL7A20Qw5gEXdBAmIJYFMhEyATNgLEIBMlGgVKSl0lFKUaBhOTk50lFKUaB9oPH2UfZQoaBqMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaCOMFnNpbXBsZV9saW5lYXJfc2NoZWR1bGWUaCV9lChoCYwIYnVpbHRpbnOUjAVmbG9hdJSTlGgKaER1aCdOaChOaCloG2gqTmgrTmgsXZRoLn2UdYaUhlIwc3WGlIZSMC4="
+    }
+}

my_first_rl_model/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8e2b788b197cceefc9cfa7cd50d167ae761a1f0e1ff317f1afdd5e28b1b0fa
+size 88362

my_first_rl_model/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db7426079fc963fde65d3a9c8a3806475ad8e7d17bf385e6d9813f60c8336c0
+size 43762

my_first_rl_model/pytorch_variables.pth

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

my_first_rl_model/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025
+- Python: 3.11.13
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.6.0+cu124
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154b9e5c2a508d971d0c048d404cf30cd3bc5c2d40124e2d4fbb8a1590bb8d78
+size 153398

results.json

@@ -0,0 +1 @@
+{"mean_reward": 260.4505752, "std_reward": 11.485522000953255, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-12T22:40:11.742787"}