Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 533.50 +/- 199.53
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 210.00 +/- 145.89
+      name: mean_reward
+      verified: false
 ---
 
 # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
@@ -35,17 +36,28 @@ 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
 
+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 utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga reachrkr -f logs/
-python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga reachrkr -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 reachrkr -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
+python -m rl_zoo3.train --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 reachrkr
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga reachrkr
 ```
 
 ## Hyperparameters
@@ -60,7 +72,7 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 1000000.0),
+             ('n_timesteps', 100000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -1,6 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
     - dqn
+  - - conf_file
+    - null
   - - device
     - auto
   - - env
@@ -41,6 +43,8 @@
     - null
   - - optimize_hyperparameters
     - false
+  - - progress
+    - false
   - - pruner
     - median
   - - sampler
@@ -50,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 875814073
+    - 2794116141
   - - storage
     - null
   - - study_name
@@ -73,3 +77,7 @@
     - null
   - - wandb_project_name
     - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -18,7 +18,7 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 1000000.0
+    - 100000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ea02c51ad747698ee06833c1a0c1e2dbf5ac6dcaeb76391eb84bb3f9eecc36
-size 27224715
+oid sha256:f5d698f7e0387732d291f05a32b81ac651d1a68f2693feb3d88fc75e596425c5
+size 13719746

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.6.0
+1.8.0a2

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb1100db0b6f79a42fc9b7749a142882679b9b6a140c30714db2f8589ac9766
-size 13505739
+oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
+size 687

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfe7f458228f072d717e250491043cd3061dfa046956c253464621509cda6fb
+oid sha256:d9cfcd9e1766805f72358e8889b276d0318eca05e35400bbf4bdc770bb354005
 size 13504937

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.4.0-62-generic-x86_64-with-glibc2.10 #70-Ubuntu SMP Tue Jan 12 12:45:47 UTC 2021
-Python: 3.8.8
-Stable-Baselines3: 1.6.0
-PyTorch: 1.12.0+cu102
-GPU Enabled: True
-Numpy: 1.20.2
-Gym: 0.21.0
+- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.10
+- Stable-Baselines3: 1.8.0a2
+- PyTorch: 1.13.1+cu116
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafdd3342b597eebb4e566bcc689b011c9cb6a17f24670ba0bdbf0251585daf3
-size 231564
+oid sha256:e38cee50b413c4b8cdda5a1434709b6fd57234bbadab18c33a59a732db44e643
+size 255939

results.json

@@ -1 +1 @@
-{"mean_reward": 533.5, "std_reward": 199.52506108256176, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-22T15:20:39.753290"}
+{"mean_reward": 210.0, "std_reward": 145.89379698945393, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T22:38:26.926819"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667a9a9090b22a281dffd993b2822a2ac16d85076d07e75b8bf3270a1c3b06de
-size 37378
+oid sha256:fa0570b193c78251d11188d295befaabb70a340db45aaf1effcd1fd2aa78d91b
+size 5845