Push to Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BreakoutNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 104.50 +/- 45.47
+      value: 42.80 +/- 16.37
       name: mean_reward
       verified: false
 ---

args.yml

@@ -12,7 +12,7 @@
   - - eval_episodes
     - 10
   - - eval_freq
-    - 25000
+    - 10000
   - - gym_packages
     - []
   - - hyperparams
@@ -20,7 +20,7 @@
   - - log_folder
     - logs/6_c/rlzoo3/
   - - log_interval
-    - -1
+    - 400
   - - max_total_trials
     - null
   - - n_eval_envs
@@ -32,7 +32,7 @@
   - - n_startup_trials
     - 10
   - - n_timesteps
-    - 1000000
+    - 500000
   - - n_trials
     - 500
   - - no_optim_plots
@@ -50,17 +50,17 @@
   - - sampler
     - tpe
   - - save_freq
-    - 100000
+    - 10000
   - - save_replay_buffer
     - false
   - - seed
-    - 2330502263
+    - 2363843725
   - - storage
     - null
   - - study_name
     - null
   - - tensorboard_log
-    - runs/BreakoutNoFrameskip-v4__dqn__2330502263__1713096824
+    - runs/BreakoutNoFrameskip-v4__dqn__2363843725__1713097209
   - - track
     - true
   - - trained_agent
@@ -76,6 +76,6 @@
   - - wandb_entity
     - null
   - - wandb_project_name
-    - dqn-breakout-gpu
+    - dqn-breakout
   - - wandb_tags
     - []

dqn-BreakoutNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7e49c22f6a089cbbf81d3a59d75a97587e605e738be0297373460ddf01dee0
-size 27203650
+oid sha256:18fb29212f83b706f1894da623327c0da8abfb5c36611b65c13f8a312c3d616b
+size 27203195

dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5af1302fc777fa403d438c95334dac43fc6f69b90f30ace0435ea0ebb2d078
-size 13498044
+oid sha256:0145c4ec10d38d4959aa379c5ad4ea0fb68771fb3d6f6c06b1e9b7221a36e076
+size 13497660

dqn-BreakoutNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f565084fcc52b4c9caec5882228a84863f58101a6d0907d758df9fda342e02fd
-size 13497178
+oid sha256:d42692dca5516497d5ab50165f41419c4b9409ac9ca31c0fe6f1f199048d1cf7
+size 13496986

dqn-BreakoutNoFrameskip-v4/system_info.txt

@@ -1,9 +1,9 @@
-- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
-- Python: 3.10.12
+- OS: Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Jan 11 04:09:03 UTC 2024
+- Python: 3.9.18
 - Stable-Baselines3: 2.1.0
-- PyTorch: 2.2.1+cu121
-- GPU Enabled: True
-- Numpy: 1.25.2
-- Cloudpickle: 2.2.1
+- PyTorch: 2.1.0+cpu
+- GPU Enabled: False
+- Numpy: 1.26.1
+- Cloudpickle: 3.0.0
 - Gymnasium: 0.29.1
 - OpenAI Gym: 0.26.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c426c9a9cc6e55742562142ddc080f38ebce56f22ae3e865b43bed976ec2fc
-size 72778
+oid sha256:57af4c35b302181eb2b6cc7a8b52df379d2738019e0a22c1c8079f5ec976cfa8
+size 73180

results.json

@@ -1 +1 @@
-{"mean_reward": 104.5, "std_reward": 45.47141959516989, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-14T13:50:20.373742"}
+{"mean_reward": 42.8, "std_reward": 16.36948380371232, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-14T19:45:56.555308"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5579a530a30fc1732198ef4494531effd410b1fe66e42f7ab340687dc4368f88
-size 50202
+oid sha256:8d588a8292d999fc90fa65f33f6b364c901d2e2bd16e8a560742025cb5e0c082
+size 40084