Initial commit

README.md

@@ -1,36 +1,69 @@
 ---
 library_name: stable-baselines3
 tags:
-- LunarLander-v2
+- SpaceInvadersNoFrameskip-v4
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: PPO
+- name: DQN
   results:
   - metrics:
     - type: mean_reward
-      value: -537.76 +/- 108.41
+      value: 607.00 +/- 156.27
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: SpaceInvadersNoFrameskip-v4
+      type: SpaceInvadersNoFrameskip-v4
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+# **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 Stable-baselines3)
-TODO: Add your code
+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)
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+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 dqn --env SpaceInvadersNoFrameskip-v4 -orga skyline22 -f logs/
+python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
 
-...
+## Training (with the RL Zoo)
+```
+python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga skyline22
+```
+
+## 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', 10000000.0),
+             ('optimize_memory_usage', True),
+             ('policy', 'CnnPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
 ```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - 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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1705736758
+  - - 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 +1,29 @@
+!!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
+    - 10000000.0
+  - - optimize_memory_usage
+    - true
+  - - 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:daf32ab623f8197cc5635062f698d49bba0ce853570ec241bb5c8f55b42a20c8
+size 27222219

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4882333b1374ae3b56cf612631cef02e793b38cabc5ea0624bba45b4186297a3
+size 13503145

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c8abfec315b7fed2d0ea1b88a63afddd87dc9818018fbb8932615770d74716
+size 13504937

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

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

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

env_kwargs.yml

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

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4950e170ce578b9e9c16d59c6d3eaa8da1d6637e21ff77492854cef9d2ba0be9
-size 75341
+oid sha256:e9de39ddeddeebcdd0b69f685c3e3f76a5945e47f471dcafc2dbdd37125f0a29
+size 209720

results.json

@@ -1 +1 @@
-{"mean_reward": -537.7599427904818, "std_reward": 108.40905184907803, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-17T13:57:26.407930"}
+{"mean_reward": 607.0, "std_reward": 156.27219842313605, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-17T17:36:41.497219"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad7f900cae942e816e1c63547f19709b625512b83016362b9b604a1cb23dd16
+size 59223