Upload trained mountain car

MountainCar-v0-onno.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c541abaed8132505dd7f6632a6b4bde5ee00877c636c34cdbcfceaca181cc67
+size 135260

MountainCar-v0-onno/_stable_baselines3_version

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

MountainCar-v0-onno/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 0x7fc5ffd111b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc5ffd11240>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc5ffd112d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc5ffd11360>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc5ffd113f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc5ffd11480>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc5ffd11510>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc5ffd115a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc5ffd11630>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc5ffd116c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc5ffd11750>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fc5ffd03e40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 32,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1673103932345024094,
+    "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:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
+    },
+    "_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": 124,
+    "n_steps": 1024,
+    "gamma": 0.9999,
+    "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
+}

MountainCar-v0-onno/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ca5e570a17eeec603afd1e33334d9470bdde80647cf9593c0aade8afacbc9e
+size 81273

MountainCar-v0-onno/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688d105948ce05ce451757fb66ca47b5a028c342885a19c1283d92f638ebfdb1
+size 39873

MountainCar-v0-onno/pytorch_variables.pth

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

MountainCar-v0-onno/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.15.0-1026-aws-x86_64-with-glibc2.35 #30-Ubuntu SMP Wed Nov 23 14:15:21 UTC 2022
+Python: 3.10.6
+Stable-Baselines3: 1.6.2
+PyTorch: 1.13.1+cu117
+GPU Enabled: True
+Numpy: 1.24.1
+Gym: 0.21.0

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -200.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **MountainCar-v0**
+This is a trained model of a **PPO** agent playing **MountainCar-v0**
+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 0x7fc5ffd111b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc5ffd11240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc5ffd112d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc5ffd11360>", "_build": "<function ActorCriticPolicy._build at 0x7fc5ffd113f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc5ffd11480>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc5ffd11510>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc5ffd115a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc5ffd11630>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc5ffd116c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc5ffd11750>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc5ffd03e40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673103932345024094, "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:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_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": 124, "n_steps": 1024, "gamma": 0.9999, "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:": "gAWV7QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXS9ob21lL29ubm8vLnZlbnYvZGVlcC1ybC1jbGFzcy9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMXS9ob21lL29ubm8vLnZlbnYvZGVlcC1ybC1jbGFzcy9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-1026-aws-x86_64-with-glibc2.35 #30-Ubuntu SMP Wed Nov 23 14:15:21 UTC 2022", "Python": "3.10.6", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.1", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-07T15:11:11.662900"}