Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 6.50 +/- 16.29
+      value: 577.50 +/- 116.86
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -37,7 +37,7 @@ 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 Beyko7 -f logs/
+python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga BekirTaha -f logs/
 python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
@@ -45,7 +45,7 @@ python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 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 Beyko7
+python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga BekirTaha
 ```
 
 ## Hyperparameters
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 100000.0),
+             ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -50,7 +50,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1360778605
+    - 2591579120
   - - storage
     - null
   - - study_name

config.yml

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

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a4b12e457c7c3c1d7904da5b719e38ee0302db80548f4a7c5a03b768835866
-size 13719817
+oid sha256:af925d692725c249a156388936bc752be8ce0d3511da0b6628607b98e0741aa1
+size 27224877

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a21ae67866ddb856ecbb70c8ba0e04af200cc5da53fbcb90e773d87e996b31
-size 687
+oid sha256:bc6245c9a909b4d6c5a9e5234b9cd728446c9a552e28d3516ffcbd78c22d11dd
+size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d9dfe84033df5be0afbe3d5d48fcc1811c153f995e154d6064e144bbd58a38
+oid sha256:231804ff419f91b457fba65028100f56605ab88734d06aacac9f50f2e928fa2d
 size 13504937

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec26970276c80c00636ff43ee53dfe8e2e18fb4695a48055e8a79c88e18cdca
-size 256433
+oid sha256:f486acd318d14610f31453bd31c9ccb8c6a79e3a59bb7cd56490fc01ba78b81e
+size 191591

results.json

@@ -1 +1 @@
-{"mean_reward": 6.5, "std_reward": 16.28649747490233, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-02T13:34:58.754177"}
+{"mean_reward": 577.5, "std_reward": 116.85995892520243, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-03T07:41:19.220815"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628daf96029cc8ce9c26184f660fbde05de90ac5274d4873ac47f46cd005eb09
-size 5739
+oid sha256:eae0a6123f93268f5f39f8a9a1e62bdc4ff7ad5e4a48152d283aeab404f845df
+size 37081