Initial commit

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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 +1,78 @@
+---
+library_name: stable-baselines3
+tags:
+- CarRacing-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 205.45 +/- 120.65
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CarRacing-v0
+      type: CarRacing-v0
+---
+
+# **PPO** Agent playing **CarRacing-v0**
+This is a trained model of a **PPO** agent playing **CarRacing-v0**
+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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo ppo --env CarRacing-v0 -orga Chris1 -f logs/
+python enjoy.py --algo ppo --env CarRacing-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env CarRacing-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env CarRacing-v0 -f logs/ -orga Chris1
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('env_wrapper',
+              [{'utils.wrappers.FrameSkip': {'skip': 2}},
+               {'gym.wrappers.resize_observation.ResizeObservation': {'shape': 64}},
+               {'gym.wrappers.gray_scale_observation.GrayScaleObservation': {'keep_dim': True}}]),
+             ('frame_stack', 2),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.99),
+             ('learning_rate', 'lin_1e-4'),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 8),
+             ('n_epochs', 10),
+             ('n_steps', 512),
+             ('n_timesteps', 4000000.0),
+             ('normalize', "{'norm_obs': False, 'norm_reward': True}"),
+             ('policy', 'CnnPolicy'),
+             ('policy_kwargs',
+              'dict(log_std_init=-2, ortho_init=False, activation_fn=nn.GELU, '
+              'net_arch=[dict(pi=[256], vf=[256])], )'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('vf_coef', 0.5),
+             ('normalize_kwargs', {'norm_obs': False, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - CarRacing-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - 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
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3969982923
+  - - 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

config.yml

@@ -0,0 +1,45 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - env_wrapper
+    - - utils.wrappers.FrameSkip:
+          skip: 2
+      - gym.wrappers.resize_observation.ResizeObservation:
+          shape: 64
+      - gym.wrappers.gray_scale_observation.GrayScaleObservation:
+          keep_dim: true
+  - - frame_stack
+    - 2
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - lin_1e-4
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 512
+  - - n_timesteps
+    - 4000000.0
+  - - normalize
+    - '{''norm_obs'': False, ''norm_reward'': True}'
+  - - policy
+    - CnnPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False, activation_fn=nn.GELU, net_arch=[dict(pi=[256],
+      vf=[256])], )
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.5

env_kwargs.yml

@@ -0,0 +1 @@
+{}

ppo-CarRacing-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fabb83aa85d2f5473c59773041fe38a4c884be6918f9d89b665806612d1fdfc
+size 10489345

ppo-CarRacing-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

ppo-CarRacing-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a248ca685bd6315971a2cc7ed58ba9055b2bc815344a9f3e77de4229ad488d4
+size 6919116

ppo-CarRacing-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a619aebae97e22c8ae784a17266b7ff7e3cae092e81d7faeef64f5dfb2912b2f
+size 3458290

ppo-CarRacing-v0/pytorch_variables.pth

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

ppo-CarRacing-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.15.0-41-generic-x86_64-with-glibc2.29 #44~20.04.1-Ubuntu SMP Fri Jun 24 13:27:29 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.6.0
+PyTorch: 1.12.0+cu113
+GPU Enabled: True
+Numpy: 1.23.1
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd80473e2f77555be3f3d53d393ee24ebb07a3fe377dc0c27bee5e91d8300ec
+size 722576

results.json

@@ -0,0 +1 @@
+{"mean_reward": 205.44836270000002, "std_reward": 120.64574667987408, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T22:26:00.735175"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f681d5edf008e282d98ebeeda71464645dd898554f96ee6699acd8c64c4cfe6
+size 303758

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2999f7e591bea179590b6118bec575a6c7aabc30610127a2ef8588930180b93e
+size 53129