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

@@ -1,3 +1,97 @@
----
-license: mit
----
+---
+library_name: stable-baselines3
+tags:
+- CarRacing-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: RecurrentPPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CarRacing-v3
+      type: CarRacing-v3
+    metrics:
+    - type: mean_reward
+      value: 384.92 +/- 161.14
+      name: mean_reward
+      verified: false
+---
+
+# **RecurrentPPO** Agent playing **CarRacing-v3**
+This is a trained model of a **RecurrentPPO** agent playing **CarRacing-v3**
+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
+SBX (SB3 + Jax): https://github.com/araffin/sbx
+
+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 ppo_lstm --env CarRacing-v3 -orga frankcholula -f logs/
+python -m rl_zoo3.enjoy --algo ppo_lstm --env CarRacing-v3  -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 ppo_lstm --env CarRacing-v3 -orga frankcholula -f logs/
+python -m rl_zoo3.enjoy --algo ppo_lstm --env CarRacing-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo_lstm --env CarRacing-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo_lstm --env CarRacing-v3 -f logs/ -orga frankcholula
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('env_wrapper',
+              [{'rl_zoo3.wrappers.YAMLCompatResizeObservation': {'shape': [64,
+                                                                           64]}},
+               {'gymnasium.wrappers.transform_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', 'CnnLstmPolicy'),
+             ('policy_kwargs',
+              'dict(log_std_init=-2, ortho_init=False, '
+              'enable_critic_lstm=False, activation_fn=nn.GELU, '
+              'lstm_hidden_size=128, )'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('vf_coef', 0.5),
+             ('normalize_kwargs', {'norm_obs': False, 'norm_reward': False})])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,85 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo_lstm
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - CarRacing-v3
+  - - env_kwargs
+    - null
+  - - eval_env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1567341068
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/CarRacing-v3__ppo_lstm__1567341068__1754953879
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - trial_id
+    - null
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - frankcholula
+  - - wandb_project_name
+    - Flow Planner
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,45 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - env_wrapper
+    - - rl_zoo3.wrappers.YAMLCompatResizeObservation:
+          shape:
+          - 64
+          - 64
+      - gymnasium.wrappers.transform_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
+    - CnnLstmPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False, enable_critic_lstm=False, activation_fn=nn.GELU,
+      lstm_hidden_size=128, )
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.5

env_kwargs.yml

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

ppo_lstm-CarRacing-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e230e2e9aea83f7d4c5e8e2d52805a46742592556c2ade128c7bbe7132721670
+size 12057989

ppo_lstm-CarRacing-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.7.0

ppo_lstm-CarRacing-v3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877919747695dff5aec22c5341dcfb493835dcbbf1832a4b6663eb8bcbc26424
+size 7968056

ppo_lstm-CarRacing-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01b12ceca96b2e1247ede1819873c6a5f5c1f60afb3f73f196ecf484d5cb1a4
+size 3985267

ppo_lstm-CarRacing-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
+size 1261

ppo_lstm-CarRacing-v3/system_info.txt

@@ -0,0 +1,8 @@
+- OS: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Tue Nov 5 00:21:55 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.7.0
+- PyTorch: 2.7.1+cu126
+- GPU Enabled: True
+- Numpy: 2.2.6
+- Cloudpickle: 3.1.1
+- Gymnasium: 1.2.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e929a8f9d1ba42e5bf95dcb5ff37a4538bbd5a504b9629cb20219e5ff5da3d
+size 569728

results.json

@@ -0,0 +1 @@
+{"mean_reward": 384.9226677, "std_reward": 161.14337186371696, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-12T09:01:21.933603"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa9e5b48b2ff85c579e37cc7ae2c17c9d9e17e2f5aae5de2d8882c16ad96487
+size 133401

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7cdf31f713d2fdce49ce8434936eda5994c79f4fbece4bdc8aa3055d2fa057
+size 50983