Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: MountainCarContinuous-v0
     metrics:
     - type: mean_reward
-      value: -66.03 +/- 0.27
+      value: 85.01 +/- 2.53
       name: mean_reward
       verified: false
 ---

args.yml

@@ -56,13 +56,13 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3581364082
+    - 122093306
   - - storage
     - null
   - - study_name
     - null
   - - tensorboard_log
-    - runs/MountainCarContinuous-v0__ppo__3581364082__1755345830
+    - runs/MountainCarContinuous-v0__ppo__122093306__1755347236
   - - track
     - true
   - - trained_agent

ppo-MountainCarContinuous-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3614d4136b8759d1115d7490633d19a0b6f3f25d56111539cbb07cb49673e37
-size 138026
+oid sha256:b6ab25b906942faf2b9d15bd8a81e7e8f7244d8eb573baf25994546e15790c5f
+size 138717

ppo-MountainCarContinuous-v0/data

@@ -4,20 +4,20 @@
         ":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 0x7ff9e524c3a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9e524c430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9e524c4c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9e524c550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7ff9e524c5e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7ff9e524c670>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff9e524c700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9e524c790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7ff9e524c820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9e524c8b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9e524c940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9e524c9d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f062a3a43a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f062a3a4430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f062a3a44c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f062a3a4550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f062a3a45e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f062a3a4670>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f062a3a4700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f062a3a4790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f062a3a4820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f062a3a48b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f062a3a4940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f062a3a49d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ff9e5242600>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f063b273e80>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -29,13 +29,13 @@
     "_num_timesteps_at_start": 0,
     "seed": 0,
     "action_noise": null,
-    "start_time": 1755345832430230034,
+    "start_time": 1755347238713099672,
     "learning_rate": {
         ":type:": "<class 'stable_baselines3.common.utils.ConstantSchedule'>",
         ":serialized:": "gAWVTQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/FF5b1emsAXNiLg==",
         "val": 7.77e-05
     },
-    "tensorboard_log": "runs/MountainCarContinuous-v0__ppo__3581364082__1755345830/MountainCarContinuous-v0",
+    "tensorboard_log": "runs/MountainCarContinuous-v0__ppo__122093306__1755347236/MountainCarContinuous-v0",
     "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -43,7 +43,7 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVfgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAD7Yw6/AAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsChpSMAUOUdJRSlC4="
+        ":serialized:": "gAWVfgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAC5Q/O+AAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsChpSMAUOUdJRSlC4="
     },
     "_episode_num": 0,
     "use_sde": true,
@@ -52,7 +52,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVEgcAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwANX/YJ3PiWMAWyUTecDjAF0lEdADc5NoJzDGnV9lChoBke/+engpBomHGgHTecDaAhHQBocKsuFpPB1fZQoaAZHQFeFvkiliz9oB03FA2gIR0Aib+qBEroXdX2UKGgGR0BYf3zcynDSaAdNjwFoCEdAJJzuF6AvtnV9lChoBkdAWF6l3yI552gHTW0BaAhHQCab1mJ3xF11fZQoaAZHQFhRu5jH4oJoB007AWgIR0Aomfq5byH3dX2UKGgGR0BYVqaTfR/maAdNlgFoCEdAKwRUvPC2t3V9lChoBkdAWHIwudwvQGgHTUwBaAhHQC0AuCf6Gg11fZQoaAZHQFew1Tzd1uBoB0v9aAhHQC5/sqrilzl1fZQoaAZHQFfKCvX9R79oB00JAWgIR0AwAbi6xxDLdX2UKGgGR0BWPLQTmGM5aAdNNwFoCEdAMOhIvrWy1XV9lChoBkdAVzpFkQPI4mgHS9doCEdAMXKfnOjZc3V9lChoBkdAV0b9wWFewGgHTZ0BaAhHQDKP0wrUb1h1fZQoaAZHQFZ4vV3EAHVoB01bAWgIR0AzehGpda+wdX2UKGgGR0BWMJTMqz7eaAdLt2gIR0Az+NR3u/lAdX2UKGgGR0BWpP69CeEqaAdLl2gIR0A0Z0Kqn3tbdX2UKGgGR0BWfW0Z3s5XaAdLomgIR0A06FqBVdX1dX2UKGgGR0BWKdTxXnyNaAdL52gIR0A1moHcDbJwdX2UKGgGR0BWkyblRxcWaAdLj2gIR0A2DCe2/i5vdX2UKGgGR0BWNeJxeb/faAdLkWgIR0A2cDneSB9UdX2UKGgGR0BWMFBUrCm/aAdLlGgIR0A21UVzp5eJdX2UKGgGR0BV7DWCmMwUaAdLmGgIR0A3OyNn5BTodX2UKGgGR0BWCXLidat+aAdLnGgIR0A3mkKeCkGidX2UKGgGR0BWBP/zasZHaAdLnWgIR0A4BRBeHBUJdX2UKGgGR0BWQXsTnJT3aAdLk2gIR0A4aV/+bVjJdX2UKGgGR0BWJWy9mHxjaAdLmGgIR0A4yU83dbgTdX2UKGgGR0BWiLdznzQNaAdLmmgIR0A5Lz8gpz91dX2UKGgGR0BWBVNg0CRwaAdLpWgIR0A5nvRZ2ZAqdX2UKGgGR0BWbZkf9xZMaAdLpmgIR0A6HCtihFmWdX2UKGgGR0BTtTcEeQuFaAdNRgFoCEdAOwOdsi0OVnV9lChoBkfASqjyDqW1MWgHTecDaAhHQD3wZ9/jKgZ1fZQoaAZHwC/sGNaQmu1oB03nA2gIR0BAUAl4TsY3dX2UKGgGR0BVOEU9IPK/aAdNSwFoCEdAQMbNr0rbxnV9lChoBkfAEXg6U7jkuGgHTecDaAhHQEIyDh99c8l1fZQoaAZHwCSRvBJqZc9oB03nA2gIR0BDjwpWmxdIdX2UKGgGR0BVPKVhTfixaAdNVwFoCEdARASs6q8143V9lChoBkdAU5skGA08/2gHTagBaAhHQESWkka/ATJ1fZQoaAZHQFXvWkadc0NoB0upaAhHQETQsK9f1Hx1fZQoaAZHQFXmS75Ec81oB0upaAhHQEUM21lXiit1fZQoaAZHQFcPUHpr1uloB0u5aAhHQEVUlyimEXd1fZQoaAZHQFYQESuhbnpoB0vBaAhHQEWhQhwEQoV1fZQoaAZHQFaC6QNkOI9oB0u2aAhHQEXoZKnNxER1fZQoaAZHQFQcQEZBLPFoB003AWgIR0BGZCWmgrYodX2UKGgGR0BVoxoqTbFkaAdNCQFoCEdARsPuqm0mdHV9lChoBkdAVSzSThYNiGgHTT4BaAhHQEc0L876pHZ1fZQoaAZHQFczzhgmZ3NoB0v2aAhHQEeF6DXe3x51fZQoaAZHQFefA7PppvhoB0vraAhHQEfVj2Bas6t1fZQoaAZHQFYlCWNWEK5oB00JAWgIR0BIMXZGrjo7dX2UKGgGR0BWB0LlV94NaAdNNgFoCEdASJsAggX/HnV9lChoBkdAV31u76Hj62gHS/loCEdASPQHu7YkFHV9lChoBkdAV2HPyCnP3WgHTRYBaAhHQElca4tpVS51fZQoaAZHQFc2jBVMmF9oB00JAWgIR0BJxPCuU2UCdX2UKGgGR0BX6EAggX/HaAdNjAFoCEdASlUzdk8RtnV9lChoBkdAV2nSPU8V6GgHS/1oCEdASq/tpmEoOXV9lChoBkdAV7cb0e2d/mgHS4xoCEdASt/jMmnfmHV9lChoBkdAV6THcUM5O2gHS6poCEdASxsdT5wfhnV9lChoBkdAV1e40/GEPGgHTSMBaAhHQEuAaw2VE/l1fZQoaAZHQFXnT1TR6WxoB03IAWgIR0BMIgFotcv/dWUu"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -102,14 +102,14 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x7ff9f478dab0>",
-        "reset": "<function RolloutBuffer.reset at 0x7ff9f478db40>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7ff9f478dbd0>",
-        "add": "<function RolloutBuffer.add at 0x7ff9f478dc60>",
-        "get": "<function RolloutBuffer.get at 0x7ff9f478dcf0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7ff9f478dd80>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7f0639865ab0>",
+        "reset": "<function RolloutBuffer.reset at 0x7f0639865b40>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f0639865bd0>",
+        "add": "<function RolloutBuffer.add at 0x7f0639865c60>",
+        "get": "<function RolloutBuffer.get at 0x7f0639865cf0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f0639865d80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ff9f4783b40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f0639868280>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 256,

ppo-MountainCarContinuous-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4de05d7dc716ad1d4a4534a0f55e0670ab56503b630f44f02ad199cb07926a
+oid sha256:e53b45058f494faef27b60e0531499443654b20a4dc53a8e56062b873a0ed56b
 size 82542

ppo-MountainCarContinuous-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a8c0bd9e3eaff8ed90b073aa82fc0aabf52d6413db9ac7f22c59d8e28a0a16
+oid sha256:9821bc26753873e6a15f53a4c9c467f73c30ed9cdb41bbda5bfb7d46f8ff5f22
 size 40764

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:251b96341bea0c8c25ee5286b3ed5e677a017f7ba28a672a1532291b8e17f599
-size 212950
+oid sha256:d2e9089aa8788349a8ff43c7090538b0409dfcdd8de5a47e7a214691539f749d
+size 168768

results.json

@@ -1 +1 @@
-{"mean_reward": -66.0250368, "std_reward": 0.26547952823138776, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T13:24:37.249650"}
+{"mean_reward": 85.005738, "std_reward": 2.525246770575264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T13:29:53.468107"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898075b6c59e72264a1c4bb4586d0a2cd7728158ad4ac9a67bd0e72175ef4478
-size 1217
+oid sha256:8467b4d0aee953031ccbc0c6f6d4c9e09e3c6bf20c63be12d97c7c4465df2c3f
+size 1644

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4bd24d22006ccade2d9d9b270ee6b2de7778c297eb64adf1e7d4c0bdbb5af0
+oid sha256:e3476d1d96467e02be16e464352492f3b9eb8a6c30624e8d123a5d96d1264cc1
 size 1869