Initial commit

.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
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Ant-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Ant-v1
+      type: seals/Ant-v1
+    metrics:
+    - type: mean_reward
+      value: 1004.15 +/- 26.60
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **seals/Ant-v1**
+This is a trained model of a **SAC** agent playing **seals/Ant-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo sac --env seals/Ant-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Ant-v1  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo sac --env seals/Ant-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Ant-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env seals/Ant-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env seals/Ant-v1 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('buffer_size', 1000000),
+             ('gamma', 0.98),
+             ('learning_rate', 0.0018514039303149058),
+             ('learning_starts', 1000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'log_std_init': -2.2692589009754176,
+               'net_arch': [256, 256],
+               'use_sde': False}),
+             ('tau', 0.05),
+             ('train_freq', 64),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - hyperparams/python/sac.py
+  - - device
+    - cpu
+  - - env
+    - seals/Ant-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 339003414
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - buffer_size
+    - 1000000
+  - - gamma
+    - 0.98
+  - - learning_rate
+    - 0.0018514039303149058
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - log_std_init: -2.2692589009754176
+      net_arch:
+      - 256
+      - 256
+      use_sde: false
+  - - tau
+    - 0.05
+  - - train_freq
+    - 64

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ed1b56b5eda9be49af251cc784ac6ecde4042ab6e958fcd18172c91baaefe3
+size 1213986

results.json

@@ -0,0 +1 @@
+{"mean_reward": 1004.1500469999999, "std_reward": 26.598463652396816, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:54:05.812092"}

sac-seals-Ant-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b212f1241b20395c023d19745794285aad2bd2e1b8060675aa3b6b5f70a0fdd5
+size 3402065

sac-seals-Ant-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.0a3

sac-seals-Ant-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e09680857f0154f1cf9c65dd9485bd3989d6bb12999445f6e740275897e74e2
+size 626845

sac-seals-Ant-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afa47b5c64a31315b2d74419c08310eedbf1dd25a4968eb6fc95d008d1235e2
+size 1221625

sac-seals-Ant-v1/data

@@ -0,0 +1,129 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
+        "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function SACPolicy.__init__ at 0x7f6db57d6700>",
+        "_build": "<function SACPolicy._build at 0x7f6db57d6790>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f6db57d6820>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f6db57d68b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f6db57d6940>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f6db57d69d0>",
+        "forward": "<function SACPolicy.forward at 0x7f6db57d6a60>",
+        "_predict": "<function SACPolicy._predict at 0x7f6db57d6af0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f6db57d6b80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6db57cdb10>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ],
+        "log_std_init": -2.2692589009754176,
+        "use_sde": false
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152660236841,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVXQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJboAAAAAAAAAHVlbsbbNAhA68iY6Ew36L9VeLMk5J7QP3bw+ulWItE/w8SwpKp61z9AupfMbjjsP6yjY88nMsC//ubG/vIi4D/1RcKIIa/gP140oTgByOC/Z06M9g048L8w9u+TRarRvyfym871jfO/7NsB3jtc2r8c8KtSLsfwP22mq1OKLbE/Mhfcgcq/tb843zXt5hY1P6pcHN43b8I/4WW6W3iD2z/wqRKMENvUP1epU4PDoui/RAkywICxsj81XKYDU3UcP2w7PEiHzdk/AOu8S6H1xj+AM0lDs6+BP2QYxZvo/7I/VIEqVhnw67+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLHYaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQI1E4Xdj5KyMAWyUTegDjAF0lEdAjKMky1uzhXV9lChoBkdAi11reZXuE2gHTegDaAhHQIyrIK2KEWZ1fZQoaAZHQI2597Uoa1loB03oA2gIR0CMs3w6QvHtdX2UKGgGR0CNj8J53TuwaAdN6ANoCEdAjLuSro4dZXV9lChoBkdAjH3PvSc9XGgHTegDaAhHQIzD87W/ag51fZQoaAZHQI3e3oRqXWxoB03oA2gIR0CMzEf29L6DdX2UKGgGR0CN49QkX1rZaAdN6ANoCEdAjNRsolUp/nV9lChoBkdAkCObIYFaCGgHTegDaAhHQIzclQ66reZ1fZQoaAZHQI+9b4+KTB9oB03oA2gIR0CM5L7VJ+UhdX2UKGgGR0CNyp+6y0KJaAdN6ANoCEdAjOzgxBVuJnV9lChoBkdAjYv0U47zTWgHTegDaAhHQIz1HFDOTq11fZQoaAZHQIbslIGyHEdoB03oA2gIR0CM/UoR7JGOdX2UKGgGR0CNg44I8hcJaAdN6ANoCEdAjQWSteUpu3V9lChoBkdAjm/qjJuEVWgHTegDaAhHQI0Nqjk+5e91fZQoaAZHQI1A8/MW43FoB03oA2gIR0CNFatkFwDOdX2UKGgGR0CNYFFnZkCnaAdN6ANoCEdAjR4BM8HObHV9lChoBkdAjkdxXGOuJWgHTegDaAhHQI0mWaz/p+t1fZQoaAZHQI3BeUB4lhRoB03oA2gIR0CNLqTjebd8dX2UKGgGR0CNPJ9AHE/CaAdN6ANoCEdAjTcPLowEhnV9lChoBkdAj089ic5Ke2gHTegDaAhHQI0/V9lVcUx1fZQoaAZHQI9zY1rIo3JoB03oA2gIR0CNR6/Yao/BdX2UKGgGR0CKXtgH/tIDaAdN6ANoCEdAjVAT4DcM3XV9lChoBkdAjQmKS5iEx2gHTegDaAhHQI1YHI4lyBF1fZQoaAZHQI9vNdE9dNZoB03oA2gIR0CNYB9zfaYedX2UKGgGR0COsHJmNBGAaAdN6ANoCEdAjWhIKD0163V9lChoBkdAjy4vMbFS9GgHTegDaAhHQI1waL876pJ1fZQoaAZHQI1TbnX/YJ5oB03oA2gIR0CNeM14Pf8/dX2UKGgGR0CO+enJDE3saAdN6ANoCEdAjYDJY1YQrnV9lChoBkdAjwn2Nm16V2gHTegDaAhHQI2IxVsDW9V1fZQoaAZHQIz40brC3w1oB03oA2gIR0CNkOx/ustDdX2UKGgGR0CPjan1FpfyaAdN6ANoCEdAjZjC6xxDLXV9lChoBkdAjyoVjiGWU2gHTegDaAhHQI2g7h99c8l1fZQoaAZHQI1XhvBJqZdoB03oA2gIR0CNqNlpXZGsdX2UKGgGR0COe6oiLVFyaAdN6ANoCEdAjbC/2bobGXV9lChoBkdAjveKP4mCy2gHTegDaAhHQI24zOX3QD51fZQoaAZHQI5gv2TPjXFoB03oA2gIR0CNwNd0JWvKdX2UKGgGR0CPxsp3HJcPaAdN6ANoCEdAjcjw7DEWI3V9lChoBkdAkJztNFjNIWgHTegDaAhHQI3RFWluWKN1fZQoaAZHQIzARXbM5fdoB03oA2gIR0CN2TJpWV/udX2UKGgGR0CLSxBkZrHmaAdN6ANoCEdAjeFQ3YL9dnV9lChoBkdAjp2AhKUVz2gHTegDaAhHQI3pS9ytFKF1fZQoaAZHQI9Opsyi22JoB03oA2gIR0CN8VIKc/dJdX2UKGgGR0CNaVXpW3jNaAdN6ANoCEdAjflaF23az3V9lChoBkdAjTQLwnYxtmgHTegDaAhHQI4BmVVxS511fZQoaAZHQI8NPc+JP69oB03oA2gIR0COCa7YkE9udX2UKGgGR0COy87Wd3B6aAdN6ANoCEdAjhIOEVWS2nV9lChoBkdAjsAY3FUADWgHTegDaAhHQI4aJq20AtF1fZQoaAZHQIysz67/XGxoB03oA2gIR0COIidc0LtvdX2UKGgGR0CP9u5Gz8gqaAdN6ANoCEdAjiow482aUnV9lChoBkdAi96vO6d1+2gHTegDaAhHQI4x8th/iHZ1fZQoaAZHQI2LkM3IdU9oB03oA2gIR0COOdOtW+49dX2UKGgGR0CIrHTDwYtQaAdN6ANoCEdAjkGXR5TqB3V9lChoBkdAj9MddNWU8mgHTegDaAhHQI5JbPWxyGV1fZQoaAZHQI/Eoh0Qsf9oB03oA2gIR0COUX0YCQtBdX2UKGgGR0COLfMEidJ8aAdN6ANoCEdAjlmrNfPX1HV9lChoBkdAi6YFmFrVOWgHTegDaAhHQI5itIK+i8F1fZQoaAZHQI4qbTQVsUJoB03oA2gIR0COaxcB2fTTdX2UKGgGR0CMHu2606YFaAdN6ANoCEdAjnMyEUTL4nV9lChoBkdAi4NwiiZfD2gHTegDaAhHQI57Ov8qFyt1fZQoaAZHQJAed4ptrKxoB03oA2gIR0COg1ShrWRSdX2UKGgGR0CO+6dU83dcaAdN6ANoCEdAjoumGmDUVnV9lChoBkdAjmAVfeDWb2gHTegDaAhHQI6T+hdt2s91fZQoaAZHQI00vY8Md95oB03oA2gIR0COnEOkLx7RdX2UKGgGR0CPV5uNPxhEaAdN6ANoCEdAjqSDVhCtzXV9lChoBkdAjovMPJ7swGgHTegDaAhHQI6sdR3u/lB1fZQoaAZHQI732/gzguRoB03oA2gIR0COtLP+n62wdX2UKGgGR0CNtJBX0XgtaAdN6ANoCEdAjrzq1og3cnV9lChoBkdAjclHcDbJwWgHTegDaAhHQI7E6Skj5bh1fZQoaAZHQI4V0GRmseZoB03oA2gIR0COzQHvc8DCdX2UKGgGR0COxvs+FDfFaAdN6ANoCEdAjtUQjt5UtXV9lChoBkdAje3S6MBIWmgHTegDaAhHQI7ctDc/MW51fZQoaAZHQIvk79GZuyhoB03oA2gIR0CO5Mw9q1w6dX2UKGgGR0CQa1/8l5WzaAdN6ANoCEdAju0MEaESNHV9lChoBkdAja0qeCkGimgHTegDaAhHQI71BrN4Z/F1fZQoaAZHQI7hZ60IC2doB03oA2gIR0CO/U87p3X7dX2UKGgGR0CQfdDkELYxaAdN6ANoCEdAjwVcBEKE4HV9lChoBkdAkDQHQ6ZH/mgHTegDaAhHQI8NgEjgQ6J1fZQoaAZHQI3i+oaUA1hoB03oA2gIR0CPFjptaY/ndX2UKGgGR0COiucBEKE4aAdN6ANoCEdAjx4HH/95yHV9lChoBkdAi/qZpBX0XmgHTegDaAhHQI8l7YbsF+x1fZQoaAZHQI5xR8c+7lJoB03oA2gIR0CPLeDU3GXHdX2UKGgGR0CMRrVGTcIraAdN6ANoCEdAjzXchTwUg3V9lChoBkdAjge1dxAB1mgHTegDaAhHQI8+C5sj3VV1fZQoaAZHQIlv9vn8sMBoB03oA2gIR0CPRgTUy57PdX2UKGgGR0CMz1/7zkIYaAdN6ANoCEdAj05I8ZDRdHV9lChoBkdAj67TrE9+w2gHTegDaAhHQI9Wb0Dlo111fZQoaAZHQIyJsZNwiq1oB03oA2gIR0CPXl/tIClrdX2UKGgGR0COSjFcY64laAdN6ANoCEdAj2ZgQpWmxnV9lChoBkdAilMM1jy4F2gHTegDaAhHQI9uQg/1QIl1fZQoaAZHQI7O9WCEpRZoB03oA2gIR0CPdmUj9n9OdX2UKGgGR0CPq1yWAwwkaAdN6ANoCEdAj36HX/YJ3XV9lChoBkdAj21TRYzSC2gHTegDaAhHQI+Ge4I8hcJ1fZQoaAZHQI3pZlpXZGtoB03oA2gIR0CPjoaWHDaXdX2UKGgGR0COL6P/7zkIaAdN6ANoCEdAj5arzoUzsXV9lChoBkdAjPYpiiItUWgHTegDaAhHQI+et4qwyIp1fZQoaAZHQIrCi6OHWSVoB03oA2gIR0CPpyn/kvK2dX2UKGgGR0COJYNrj5sTaAdN6ANoCEdAj69s90RvnHV9lChoBkdAj8dZR0lqrWgHTegDaAhHQI+3jG3nZCh1fZQoaAZHQI0eePeYUnJoB03oA2gIR0CPv6pn6EamdX2UKGgGR0COTVGOuJUHaAdN6ANoCEdAj8eixu89OnVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 15610,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False]",
+        "_shape": [
+            29
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVjAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAACAvwAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjAQtMS4wlIwJaGlnaF9yZXBylIwDMS4wlIwKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlIwFUENHNjSUaDGMFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaDyKEONhlaa3XlgJLUWWWTS1oRqMA2luY5SKEKlzeES8M4FYghr3OtvajUF1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu",
+        "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": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1,
+    "batch_size": 512,
+    "learning_starts": 1000,
+    "tau": 0.05,
+    "gamma": 0.98,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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 n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f6db5823700>",
+        "add": "<function ReplayBuffer.add at 0x7f6db5823790>",
+        "sample": "<function ReplayBuffer.sample at 0x7f6db5823820>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f6db58238b0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f6db581c820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6db581c840>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

sac-seals-Ant-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6188361c13d2ce04327d1ed75d95229a15f4d7cd6420552793706998cbe00d96
+size 1507

sac-seals-Ant-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a082101a2a842f84130d6bd17cc93e477490b979c9403189310809adac7e8976
+size 1533253

sac-seals-Ant-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ec2892a29f7f53a942ba6225998a5b666a9ee2ce7c1923d59a24785964308c
+size 747

sac-seals-Ant-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.2.0a3
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56124deccc53907b7f489dc0d43878a1d2b1a91f0b09055d79d130e20ea157f
+size 29198