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

@@ -1,35 +1,86 @@
 ---
-library_name: ml-agents
+library_name: stable-baselines3
 tags:
-- Huggy
+- SpaceInvadersNoFrameskip-v4
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-Huggy
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 712.00 +/- 195.22
+      name: mean_reward
+      verified: false
 ---
 
-  # **ppo** Agent playing **Huggy**
-  This is a trained model of a **ppo** agent playing **Huggy**
-  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
 
-  ## Usage (with ML-Agents)
-  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
 
-  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
-  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
-  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
-  - A *longer tutorial* to understand how works ML-Agents:
-  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+## Usage (with SB3 RL Zoo)
 
-  ### Resume the training
-  ```bash
-  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
-  ```
+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
 
-  ### Watch your Agent play
-  You can watch your agent **playing directly in your browser**
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
 
-  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
-  2. Step 1: Find your model_id: AliMokh/DeepRL
-  3. Step 2: Select your *.nn /*.onnx file
-  4. Click on Watch the agent play 👀
-  
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AliMokh -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -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 dqn --env SpaceInvadersNoFrameskip-v4 -orga AliMokh -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga AliMokh
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 100000),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
+             ('frame_stack', 4),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 100000),
+             ('n_timesteps', 1000000.0),
+             ('optimize_memory_usage', False),
+             ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - dqn.yml
+  - - device
+    - auto
+  - - env
+    - SpaceInvadersNoFrameskip-v4
+  - - 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
+    - 1643485488
+  - - 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 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 32
+  - - buffer_size
+    - 100000
+  - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - exploration_final_eps
+    - 0.01
+  - - exploration_fraction
+    - 0.1
+  - - frame_stack
+    - 4
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0001
+  - - learning_starts
+    - 100000
+  - - n_timesteps
+    - 1000000.0
+  - - optimize_memory_usage
+    - false
+  - - policy
+    - CnnPolicy
+  - - target_update_interval
+    - 1000
+  - - train_freq
+    - 4

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52777f169fd76dd1001d213cb09b85791a24fd93758e84b3c4b51670637e1578
+size 27220124

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.0a11

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38bba78c96d2fe0260419f89b6e31f35db92ffeb6cd01602f724e39a6058bc1
+size 13506236

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6879e61b822f9847746208ea26c1a59ecb34c288eb89e90a253a6707e14c6b8f
+size 13505370

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.2.0a11
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

env_kwargs.yml

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

results.json

@@ -1 +1 @@
-{"mean_reward": 267.1144651, "std_reward": 14.631091205567042, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-06T16:18:13.936139"}
+{"mean_reward": 712.0, "std_reward": 195.22038827950323, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-09T15:51:02.682028"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbcb1235ff90a34797f981cc856d4b16b3841fd9f281dc7c23cbcc3d4c20bb9
+size 36605