Initial commit

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: DQN
+- name: QRDQN
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 220.00 +/- 67.56
+      value: 660.00 +/- 181.16
       name: mean_reward
       verified: false
 ---
 
-# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
-This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
+# **QRDQN** Agent playing **SpaceInvadersNoFrameskip-v4**
+This is a trained model of a **QRDQN** 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).
 
@@ -43,39 +43,31 @@ pip install rl_zoo3
 
 ```
 # Download model and save it into the logs/ folder
-python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga dylwil3 -f logs/
-python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga dylwil3 -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --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 dylwil3 -f logs/
-python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga dylwil3 -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+python -m rl_zoo3.train --algo qrdqn --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 dylwil3
+python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga dylwil3
 ```
 
 ## Hyperparameters
 ```python
-OrderedDict([('batch_size', 64),
-             ('buffer_size', 10000),
-             ('env_wrapper',
+OrderedDict([('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
-             ('exploration_final_eps', 0.01),
-             ('exploration_fraction', 0.1),
+             ('exploration_fraction', 0.025),
              ('frame_stack', 4),
-             ('gradient_steps', 1),
-             ('learning_rate', 0.001),
-             ('learning_starts', 10000),
              ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
-             ('target_update_interval', 1000),
-             ('train_freq', 4),
              ('normalize', False)])
 ```

args.yml

@@ -1,6 +1,6 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
-    - dqn
+    - qrdqn
   - - conf_file
     - null
   - - device
@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3329225970
+    - 1302513789
   - - storage
     - null
   - - study_name

config.yml

@@ -1,29 +1,13 @@
 !!python/object/apply:collections.OrderedDict
-- - - batch_size
-    - 64
-  - - buffer_size
-    - 10000
-  - - env_wrapper
+- - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
-  - - exploration_final_eps
-    - 0.01
   - - exploration_fraction
-    - 0.1
+    - 0.025
   - - frame_stack
     - 4
-  - - gradient_steps
-    - 1
-  - - learning_rate
-    - 0.001
-  - - learning_starts
-    - 10000
   - - n_timesteps
     - 1000000.0
   - - optimize_memory_usage
     - false
   - - policy
     - CnnPolicy
-  - - target_update_interval
-    - 1000
-  - - train_freq
-    - 4

qrdqn-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c638397eaef186e232e8c438e9bc87eeb5d2ee98c13f5f86a2d0f3647c8c746a
+size 37018588

qrdqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16874494e12990e12223112de191d4c45b987ec0732958ce560806469938d49d
+size 18405963

qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e851bd2ca7822ef59b09505021c99a3a45cb8ec2d6984a380a9207ef6aae7d6b
+size 18405545

qrdqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

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

qrdqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.10.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.0+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"mean_reward": 220.0, "std_reward": 67.56478372643548, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-28T22:45:53.916782"}
+{"mean_reward": 660.0, "std_reward": 181.1629101113139, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-28T23:07:33.191456"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:592c050cbaaaf2ec57c1aaf7d02952b3c694c21294b4d9fa82866947d9b5a070
-size 46501
+oid sha256:a4e5066bfdb51f7c6753430e365afca3f5c0d96b45d5b6a21f3a282369b12468
+size 6134