Initial Commit
Browse files- README.md +8 -1
- a2c-MountainCar-v0.zip +2 -2
- a2c-MountainCar-v0/data +21 -21
- env_kwargs.yml +1 -1
- results.json +1 -1
README.md
CHANGED
|
@@ -31,7 +31,9 @@ with hyperparameter optimization and pre-trained agents included.
|
|
| 31 |
|
| 32 |
## Usage (with SB3 RL Zoo)
|
| 33 |
|
| 34 |
-
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
|
|
|
|
|
|
|
| 35 |
|
| 36 |
```
|
| 37 |
# Download model and save it into the logs/ folder
|
|
@@ -55,3 +57,8 @@ OrderedDict([('ent_coef', 0.0),
|
|
| 55 |
('policy', 'MlpPolicy'),
|
| 56 |
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
| 57 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## Usage (with SB3 RL Zoo)
|
| 33 |
|
| 34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
| 35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
| 36 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
| 37 |
|
| 38 |
```
|
| 39 |
# Download model and save it into the logs/ folder
|
|
|
|
| 57 |
('policy', 'MlpPolicy'),
|
| 58 |
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
| 59 |
```
|
| 60 |
+
|
| 61 |
+
# Environment Arguments
|
| 62 |
+
```python
|
| 63 |
+
{'goal_velocity': 0}
|
| 64 |
+
```
|
a2c-MountainCar-v0.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f37608292526f3d3eaec0feac11f0191034b47f1cbd587676431b747698f65b0
|
| 3 |
+
size 95799
|
a2c-MountainCar-v0/data
CHANGED
|
@@ -1,27 +1,27 @@
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
-
":serialized:": "
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 ",
|
| 7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
| 8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
| 9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
| 10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
| 11 |
-
"_build": "<function ActorCriticPolicy._build at
|
| 12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
| 13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
| 14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
| 15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
| 16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
| 17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
-
"_abc_impl": "<_abc_data object at
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
| 23 |
":type:": "<class 'dict'>",
|
| 24 |
-
":serialized:": "
|
| 25 |
"optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
|
| 26 |
"optimizer_kwargs": {
|
| 27 |
"alpha": 0.99,
|
|
@@ -31,7 +31,7 @@
|
|
| 31 |
},
|
| 32 |
"observation_space": {
|
| 33 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 34 |
-
":serialized:": "
|
| 35 |
"dtype": "float32",
|
| 36 |
"low": "[-1.2 -0.07]",
|
| 37 |
"high": "[0.6 0.07]",
|
|
@@ -44,7 +44,7 @@
|
|
| 44 |
},
|
| 45 |
"action_space": {
|
| 46 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 47 |
-
":serialized:": "
|
| 48 |
"n": 3,
|
| 49 |
"dtype": "int64",
|
| 50 |
"_np_random": "RandomState(MT19937)",
|
|
@@ -61,13 +61,13 @@
|
|
| 61 |
"tensorboard_log": null,
|
| 62 |
"lr_schedule": {
|
| 63 |
":type:": "<class 'function'>",
|
| 64 |
-
":serialized:": "
|
| 65 |
},
|
| 66 |
"_last_obs": null,
|
| 67 |
"_last_episode_starts": null,
|
| 68 |
"_last_original_obs": {
|
| 69 |
":type:": "<class 'numpy.ndarray'>",
|
| 70 |
-
":serialized:": "
|
| 71 |
},
|
| 72 |
"_episode_num": 0,
|
| 73 |
"use_sde": false,
|
|
@@ -75,11 +75,11 @@
|
|
| 75 |
"_current_progress_remaining": 0.0,
|
| 76 |
"ep_info_buffer": {
|
| 77 |
":type:": "<class 'collections.deque'>",
|
| 78 |
-
":serialized:": "
|
| 79 |
},
|
| 80 |
"ep_success_buffer": {
|
| 81 |
":type:": "<class 'collections.deque'>",
|
| 82 |
-
":serialized:": "
|
| 83 |
},
|
| 84 |
"_n_updates": 12500,
|
| 85 |
"n_steps": 5,
|
|
@@ -91,6 +91,6 @@
|
|
| 91 |
"normalize_advantage": false,
|
| 92 |
"_last_dones": {
|
| 93 |
":type:": "<class 'numpy.ndarray'>",
|
| 94 |
-
":serialized:": "
|
| 95 |
}
|
| 96 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 ",
|
| 7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fe534a77710>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe534a777a0>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe534a77830>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe534a778c0>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fe534a77950>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fe534a779e0>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe534a77a70>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fe534a77b00>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe534a77b90>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe534a77c20>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe534a77cb0>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc_data object at 0x7fe534a4b390>"
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
| 23 |
":type:": "<class 'dict'>",
|
| 24 |
+
":serialized:": "gASVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
|
| 25 |
"optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
|
| 26 |
"optimizer_kwargs": {
|
| 27 |
"alpha": 0.99,
|
|
|
|
| 31 |
},
|
| 32 |
"observation_space": {
|
| 33 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 34 |
+
":serialized:": "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",
|
| 35 |
"dtype": "float32",
|
| 36 |
"low": "[-1.2 -0.07]",
|
| 37 |
"high": "[0.6 0.07]",
|
|
|
|
| 44 |
},
|
| 45 |
"action_space": {
|
| 46 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
| 47 |
+
":serialized:": "gASVTQsAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpRoE4wFc3RhdGWUfZQojANrZXmUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoB4wHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAU1wAoWUaAmMAnU0lImIh5RSlChLA2gNTk5OSv////9K/////0sAdJRiiULACQAAAAAAgFPCs5yHA7WTcuyrW+jmsvLPtoHa1QbvYaExTaBrtczZE+YYn3SceS/IpRuAxHkBSZ4PQ+Rd4BiTkhNVzNRKKWTSCJW+NNCeRHJ6A/Ctvwpzm3s+6WCxBtp1A0ULbn3WFmrrBDRmg7fz9aUvae9CY0O1XPfCd1LMRkQ3LQiJbtCOrnf7GLaAT3ue+U8y7BLYuY5ehakZyq49di1nK0KAnsXuxx/1IgFdS88kD8wZUmREV5hwnQr1Ehe16VreO8T/Qc86sV+2h90z2FiJqqLNf3s/yZS3bA9DHzGZfRtgkKu3Bx0ZTN7I+466APXPqRreJf4gBqUW/NB248FO9cpD0wFaed9QV63NqpiFOs/RYeEwD8e32dZFRfi9SK5aLvuApJMu2LOfZweypHIkyPjeY5W+tsm2bdPmVoCAOiyi73cf5k0LQeJNWqZU/wuy/f8myghZ9qrjf+2JSJMaB9VNMXWmxuq4Dq0fkhzJr1ML7SgftfSG29O5koFUMozQL58gAzyX96ZMcpWbZ+3/zlaVhGln5egXC8MtIK6xIFCvh/vD/F1jLgYIp14MM597MuPmTpa+OaKek7bql9Cp8/0skhg5QSCvCaijm8wenxrfqLyRxDPCpS+L3isJC5LrjFgWnsdxQXVrJK8uaobJcTIJ5NrYYfA2l5gH27iPI9EqhzFtZJXiE4vXpH18f3kouYV9RowPzOtmYsbmstR/Mx/VY7E0XBmnMidL4dYTUXgxaDbFxWy3y6miL2yw0I2O09vPWV7LqbwMbthlU26lrLfnJDz88B+7y4pFCwvsHgCsMWq6pvroAF4Ms+++JnhzrL0GLrtfJ7667p42Vg78GirmKIRMFH0p6aLRPV4V/fclE3PLBj0InU315M5v7fDFj/IreJeFUhIAy5/BlvLdgwIfBMBWvyjhqGRBo2KmdiDAO9BPhdi6oGmZUCxTDjUyMd8rjeRdntTE+L9sHQUSvUfpRjKcSIjZXcjsMMSwwU0QzIXewD4nZg8EAZ72iHnChWveW7cB5EQRFE+YPvvyNAw4OvORF+DjDtmLUz6jNz0JbkuKbhIQEEVbpDRkoeIGA4HATymZeE4TX/hvhOxJfX5liXD9/Uon8OjJ/hhIrDNUYR2NOV2R1L+VuK/JA9o0izGPiCC9vi7UK1u4re8tvPrBInC6BH2DpMvWSRepdH0frFxGsH/kRB/S77USeMs38a+yorDaa9Wsb9WnuQg10vl087jhvwSZx77fGq52NV1h/UnZAjnqJOjCPBgQrY0wsSeSW6SOSdItAOupiWkVvSzHz+gopd/3FUUPbjdik7Vd6O6ycGOFwp4+wyZqq1MKHww5exJND6De8NB4fGBzsvKoT8O1fAC3Y2Z+3mLYwkCJXULx2zNSO90bQi0L0BhTF1AidNtqRkak72V+V1kos6m4F+kyZiOiwxfcHKWHmpQe3A8HpX6nacx0Zso0WyF/W/sOLo//2g0YD9koIjgKvw//f9Em4CvxNBUMnJYTVQJGysF4QMShnM6byaMNJhRVALf+X0+SgLJkEwLfKdBbKxjA035OEc2YKmUpvooVUUt+9U8d7cKRgNYKKPwCHyYfLJSQt4ZEdThgjeywDxgsGzPax5SklOLroSYn39feofatZDzJXevfPTHyi1ZLwpe6Hwkbqz1FuOnHiShPedbEA9b/HCtBytSZrgUwlwHpQlAiBTSxpN7TFzVZrrhRd6N8W+FeE9SAGCHwXchFR4SCGThPyRGO/XWkMPJ42BLUOmMGepDQgWH646tjoJSE3EXcA5iDS+Nq6Oh521oC2UPAnvxIj1QbVh8IbxlBytRTTjc0c14E9cyhIPlgIoHriuEFSMXSEzOGL1MmL6UCbiXfsRg9Z6OwWCCl3VeGg5bEZ1kjJkvs08k7wtPk4ATAjaTL3QoY2gf106zFbJtL4D5gmLMJ9OuzE2Fn5uaAqqpjXIqqEXxS9jtpsRU9VTHCg68RwXQVIUhuVJgHq8fOigBMrW7Am5+jjo/GNNlcFcp813dFiXy4qHhjGSEjNXp3ln03NZkOgqXQ8SalJlPOvyrAS9wW9EtjQKhcrBSWSsQ8C3o/Mc/sR/CMRB85ZIojR/tiCKtOutxQMIusIOnYHK8g6kPpTQ8J/PfJ8pa3GEoYoA67axQTXsysd2Y6ZDwpz1HkAeISVK2AlCcuQssrQv8dVLAcins/2kjRFp5Vp82HSX9j6Ci9GH5mkdyqV84vWsdwRz4JNXHZoHVZKnrxSdA1HUwRUI/5oWiqnGk9KyiS4Mv9dQIVluJ1+/pAHYEdG9YgLHiNE2zA7aIQbqqlGX6jH1CrHSPL9mnlHdPiKjozwRXu02UQuzlGJn+/PUkU6cPYLLeLc8e7S2qfCZxbdpHioand7wYKqb5bMb8dA3Dwvm6P6iJXSogJ+Q+0z43li8ydYJqZNZlSjsljr/2c5UU33vMhLDLEXIHT8WzrsS45TsKNbhYfTYx6Ds/8W5yOtiOPWc0+fRlAjbQC++FKo5UaMl2eRCxI4U5/heX2HxJGNk50rICjuFsG/8Q+NUuJgS+y3FMhe+sm1e2MdC+ldkBqEn8oRxajECbP4Wizz1tfJliW/1A5fdGTfUxM3HV72bJgnqswmoAumAx6d36KfuZwEEp0/wcrdo+8/unJ5f2mYeqCrOcaxDJrs6SxW1zVaH/YTZl+RNA0NjPLgaqnlveaes/MkpzsVEQDtvKGFrG1cnmGjZVi2azrSDGQ0Y423nEksDC5awYcOJmVYbeA4DkMSNfj+7Dx2SzH/PVPuXLX9aw9K9QF4Ml48zsSrwsVjIa8+gIdffs2pf2wCKcPtFez6vOT0UDuFHknJjMDg0fI3DnyC7jJqO8V4XpmPyarTp3JJRGhmqTHhpZInn70JMfS+RFry5+rLSOM0T+KWV8fYjs9eyCiZijlR4AiADooXm9G8JIzZCLZX2Dty83iyz7gQzSxYO7ULuTT1stvGuJwbBP4LMhLXkbxdhAmBSDiYNOnc3O+yFsO6Ps9UOQD8S4Pbr8hZ4mFjbicpO635SwpmHINYDeuewln3/GHz69LpCjmpnKPeF9ZxXcq6MR4kJUV2j/dQzqjLniNaQmrMkULdI7W1sMXRFcsz9xs1GVwVqmtMVws8HtvXMYNmosCrrgAFX2ghPz7dXCV6vML5YhfNbDAzzG6MHffrslrhMav3vtlt8Fnld4VaH6IhMkowayT1lSVvfvlKHCWwtKaTcOZrR5LZGalJOpFbVIFUOAo+LnY/25bmc3KloyLzgiTudjPsXEGPNPBIvE/5cMEvU4Lrs0N3tCke4abYDXF9f14QrwLlHSUYowDcG9zlE1wAnWMCWhhc19nYXVzc5RLAIwFZ2F1c3OURwAAAAAAAAAAdWKMBl9zaGFwZZQpdWIu",
|
| 48 |
"n": 3,
|
| 49 |
"dtype": "int64",
|
| 50 |
"_np_random": "RandomState(MT19937)",
|
|
|
|
| 61 |
"tensorboard_log": null,
|
| 62 |
"lr_schedule": {
|
| 63 |
":type:": "<class 'function'>",
|
| 64 |
+
":serialized:": "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"
|
| 65 |
},
|
| 66 |
"_last_obs": null,
|
| 67 |
"_last_episode_starts": null,
|
| 68 |
"_last_original_obs": {
|
| 69 |
":type:": "<class 'numpy.ndarray'>",
|
| 70 |
+
":serialized:": "gASVCgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOAb5kZvwAAAAC7aQK/AAAAAIUPDb8AAAAAnKvXvgAAAADtBta+AAAAAPa1Cb8AAAAASOfjvgAAAAAg6we/AAAAAC5H0L4AAAAApIP7vgAAAABToNS+AAAAABwS/L4AAAAANkoFvwAAAADC8tm+AAAAADFJz74AAAAAsSHQvgAAAACUdJRiLg=="
|
| 71 |
},
|
| 72 |
"_episode_num": 0,
|
| 73 |
"use_sde": false,
|
|
|
|
| 75 |
"_current_progress_remaining": 0.0,
|
| 76 |
"ep_info_buffer": {
|
| 77 |
":type:": "<class 'collections.deque'>",
|
| 78 |
+
":serialized:": "gASV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFVAAAAAAACMAWyUS1WMAXSUR0BxRLO/tY0VdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0BxRLronrprdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0BxRSX9itq6dX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxRUcaOxSpdX2UKGgGR8BjYAAAAAAAaAdLm2gIR0BxRbJkoWpIdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0BxRmYkVvdedX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxRmbvw3HadX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxRoPJ7sv7dX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxR022oegddX2UKGgGR8BcwAAAAAAAaAdLc2gIR0BxVHnfVI7OdX2UKGgGR8BXwAAAAAAAaAdLX2gIR0BxVMYO2AoYdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxVNfUnXumdX2UKGgGR8BkQAAAAAAAaAdLomgIR0BxVZF6Rhc8dX2UKGgGR8BjoAAAAAAAaAdLnWgIR0BxVWLxZuAJdX2UKGgGR8BdAAAAAAAAaAdLdGgIR0BxVltfoicHdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0BxVqBd2PkrdX2UKGgGR8BegAAAAAAAaAdLemgIR0BxVud4FA3UdX2UKGgGR8BdwAAAAAAAaAdLd2gIR0BxVzJRwZO0dX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxVxltj0+UdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxV4vrWy1NdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0BxV73cpLEldX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxV3XlKbrkdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0BxWIhGH58CdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxWM1tO2y+dX2UKGgGR8BdgAAAAAAAaAdLdmgIR0BxWOn/DLr5dX2UKGgGR8BcwAAAAAAAaAdLc2gIR0BxWgh2W6bwdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxWc3Mpw0gdX2UKGgGR8BdAAAAAAAAaAdLdGgIR0BxWh3OfNA1dX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxWna/RE4OdX2UKGgGR8BeAAAAAAAAaAdLeGgIR0BxWwkyDZlGdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0BxWv8l5WzXdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxW6SMcZLqdX2UKGgGR8BcgAAAAAAAaAdLcmgIR0BxXGAxzq8ldX2UKGgGR8BVwAAAAAAAaAdLV2gIR0BxXG6qbSZ0dX2UKGgGR8BcwAAAAAAAaAdLc2gIR0BxXFL9MsYmdX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxXKfNA1NydX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxXJIVdonKdX2UKGgGR8BYgAAAAAAAaAdLYmgIR0BxXUgX/HYIdX2UKGgGR8BdAAAAAAAAaAdLdGgIR0BxXQ/zJ6ppdX2UKGgGR8BkQAAAAAAAaAdLomgIR0BxXfpyIYWMdX2UKGgGR8BbwAAAAAAAaAdLb2gIR0BxXfTiKiwjdX2UKGgGR8BVgAAAAAAAaAdLVmgIR0BxXvgP3BYWdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxX1z5oGpudX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxXyMDOkckdX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxX1LrX18LdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0BxX4S6DoQndX2UKGgGR8BdgAAAAAAAaAdLdmgIR0BxX+grYoRadX2UKGgGR8BdgAAAAAAAaAdLdmgIR0BxYGyVv/BFdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0BxYJ7IDHOsdX2UKGgGR8BVgAAAAAAAaAdLVmgIR0BxYJgiNbTudX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxYXsqril0dX2UKGgGR8BdwAAAAAAAaAdLd2gIR0BxYeQ5myxBdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0BxYgtPHktFdX2UKGgGR8BdAAAAAAAAaAdLdGgIR0BxYdepn6EbdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxYpVHWjGldX2UKGgGR8BcgAAAAAAAaAdLcmgIR0BxYjDcdo38dX2UKGgGR8BVAAAAAAAAaAdLVGgIR0BxY1rsSkCWdX2UKGgGR8BdgAAAAAAAaAdLdmgIR0BxY2aOPvKEdX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxZAuEmICVdX2UKGgGR8BcgAAAAAAAaAdLcmgIR0BxZJW6shgWdX2UKGgGR8BbwAAAAAAAaAdLb2gIR0BxZPd43WFwdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxZcPatcOcdX2UKGgGR8BcAAAAAAAAaAdLcGgIR0BxZbVjI7vHdX2UKGgGR8Bi4AAAAAAAaAdLl2gIR0BxZhrl/6O6dX2UKGgGR8BjYAAAAAAAaAdLm2gIR0BxZmxzJZGKdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0BxZiyVv/BFdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxZugwoLG8dX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxZx81Gb1AdX2UKGgGR8BZAAAAAAAAaAdLZGgIR0BxZqtGNJe3dX2UKGgGR8BbwAAAAAAAaAdLb2gIR0BxZ2G1x82KdX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxZ9diUgSwdX2UKGgGR8BWQAAAAAAAaAdLWWgIR0BxaC1stTUBdX2UKGgGR8BYgAAAAAAAaAdLYmgIR0BxZ9ivxH5KdX2UKGgGR8BkoAAAAAAAaAdLpWgIR0BxaDDGcWj5dX2UKGgGR8BYgAAAAAAAaAdLYmgIR0BxaR+y7f52dX2UKGgGR8BdAAAAAAAAaAdLdGgIR0BxaLtIClrNdX2UKGgGR8BWwAAAAAAAaAdLW2gIR0BxaeECeVcEdX2UKGgGR8BbwAAAAAAAaAdLb2gIR0Bxaf+JgsshdX2UKGgGR8BXgAAAAAAAaAdLXmgIR0BxalaiblRxdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0BxaydCmdiEdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0Bxa8FMZgogdX2UKGgGR8BdAAAAAAAAaAdLdGgIR0Bxa6HVPN3XdX2UKGgGR8BcAAAAAAAAaAdLcGgIR0Bxa6/9Hc1wdX2UKGgGR8BWQAAAAAAAaAdLWWgIR0BxbDK1XvH+dX2UKGgGR8BbwAAAAAAAaAdLb2gIR0BxbF1gYxcndX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxbPUqhDgJdX2UKGgGR8BWQAAAAAAAaAdLWWgIR0BxbQ9mpVCHdX2UKGgGR8BcQAAAAAAAaAdLcWgIR0BxbUj4YaYNdX2UKGgGR8BlIAAAAAAAaAdLqWgIR0BxbWGpMpPRdX2UKGgGR8BjQAAAAAAAaAdLmmgIR0BxbeV3Ux20dX2UKGgGR8BkoAAAAAAAaAdLpWgIR0BxbZbY9Pk8dX2UKGgGR8BcAAAAAAAAaAdLcGgIR0Bxbby4FzMidX2UKGgGR8BcwAAAAAAAaAdLc2gIR0BxbxjkMkQgdX2UKGgGR8BcgAAAAAAAaAdLcmgIR0Bxby9TP0I1dX2UKGgGR8BVgAAAAAAAaAdLVmgIR0Bxb69i+cpcdX2UKGgGR8BWAAAAAAAAaAdLWGgIR0Bxb56sySFHdX2UKGgGR8BcAAAAAAAAaAdLcGgIR0Bxb4CuEEkjdX2UKGgGR8BdQAAAAAAAaAdLdWgIR0BxcHoSteUqdX2UKGgGR8BXgAAAAAAAaAdLXmgIR0Bxb/4QBgeBdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0BxcE83dbgTdWUu"
|
| 79 |
},
|
| 80 |
"ep_success_buffer": {
|
| 81 |
":type:": "<class 'collections.deque'>",
|
| 82 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 83 |
},
|
| 84 |
"_n_updates": 12500,
|
| 85 |
"n_steps": 5,
|
|
|
|
| 91 |
"normalize_advantage": false,
|
| 92 |
"_last_dones": {
|
| 93 |
":type:": "<class 'numpy.ndarray'>",
|
| 94 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
| 95 |
}
|
| 96 |
}
|
env_kwargs.yml
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
goal_velocity: 0
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": -110.6, "std_reward": 19.422667170087635, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-
|
|
|
|
| 1 |
+
{"mean_reward": -110.6, "std_reward": 19.422667170087635, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T10:14:57.746736"}
|