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: 918.00 +/- 380.21
+      value: 1603.00 +/- 724.03
       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 +43,32 @@ 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 mcaoun -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 mcaoun -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 mcaoun -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 mcaoun -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 mcaoun
+python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga mcaoun
 ```
 
 ## Hyperparameters
 ```python
-OrderedDict([('batch_size', 32),
-             ('buffer_size', 100000),
+OrderedDict([('buffer_size', 100000),
              ('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', 0.0001),
-             ('learning_starts', 100000),
              ('n_timesteps', 10000000.0),
              ('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
-    - 4287231991
+    - 1132488828
   - - storage
     - null
   - - study_name

config.yml

@@ -1,29 +1,15 @@
 !!python/object/apply:collections.OrderedDict
-- - - batch_size
-    - 32
-  - - buffer_size
+- - - buffer_size
     - 100000
   - - 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
-    - 0.0001
-  - - learning_starts
-    - 100000
   - - n_timesteps
     - 10000000.0
   - - 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 sha256:2cea7fbe1e6b350d119e91fac0847989dc3f87c1ac08ca088e4922d9793a3203
+size 37025172

qrdqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a2

qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfcb1dcdcbd508cf2a0f5409b119756e679a5f2a062743837ad7810d4de0a97
+size 18405963

qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e208801030a2516b25c3d1b52506263270426e3bfe977535e3e80a6b9e920aeb
+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 +1,7 @@
+- OS: Linux-5.4.0-144-generic-x86_64-with-glibc2.29 # 161-Ubuntu SMP Fri Feb 3 14:49:04 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 1.8.0a2
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.2
+- Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c334a2b0fa257a35df59740f8e6a2dbc8118680f3f7b785aff00b888fc0c32
-size 179568
+oid sha256:d2bae2b8844812f8297dfec4b47a81774e2c01d32ad145fb2b345ddd12ad09b6
+size 209038

results.json

@@ -1 +1 @@
-{"mean_reward": 918.0, "std_reward": 380.21178308937243, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-05T08:04:34.024555"}
+{"mean_reward": 1603.0, "std_reward": 724.0276237824079, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-05T19:03:28.884310"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96a7a01e98e7d58d67695adefec4fc9bfc1988bec717f5d3f7a909366678a83
-size 273780
+oid sha256:70632f9f4f440d1a07cb14b6a8296ac83064086e1d165eab31da23d58345a0cf
+size 244038