Hugging Face's logo

nsanghi
/
dqn-atari-breakout-rlzoo-gpu

Reinforcement Learning
stable-baselines3
BreakoutNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
nsanghi commited on
Commit
0470e29
·
1 Parent(s): 6173814

Push to Hub

Browse files
Files changed (11) hide show
  1. README.md +1 -1
  2. args.yml +3 -3
  3. dqn-BreakoutNoFrameskip-v4.zip +2 -2
  4. dqn-BreakoutNoFrameskip-v4/_stable_baselines3_version +1 -1
  5. dqn-BreakoutNoFrameskip-v4/data +0 -0
  6. dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-BreakoutNoFrameskip-v4/policy.pth +1 -1
  8. dqn-BreakoutNoFrameskip-v4/system_info.txt +4 -4
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 7.60 +/- 3.80
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 104.50 +/- 45.47
20
  name: mean_reward
21
  verified: false
22
  ---
args.yml CHANGED
@@ -32,7 +32,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - 10000000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -54,13 +54,13 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 952530566
58
  - - storage
59
  - null
60
  - - study_name
61
  - null
62
  - - tensorboard_log
63
- - runs/BreakoutNoFrameskip-v4__dqn__952530566__1699166218
64
  - - track
65
  - true
66
  - - trained_agent
 
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
+ - 1000000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2330502263
58
  - - storage
59
  - null
60
  - - study_name
61
  - null
62
  - - tensorboard_log
63
+ - runs/BreakoutNoFrameskip-v4__dqn__2330502263__1713096824
64
  - - track
65
  - true
66
  - - trained_agent
dqn-BreakoutNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac87c1c8d6ebef661f724be3d3e056b98923ddcf66651e23953b598ddd5d788c
3
- size 27203833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7e49c22f6a089cbbf81d3a59d75a97587e605e738be0297373460ddf01dee0
3
+ size 27203650
dqn-BreakoutNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.2.0a9
 
1
+ 2.1.0
dqn-BreakoutNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7720225399e139a34e0b56907eda47bb19758cc8648728dcf1951ddc3f8c699
3
  size 13498044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5af1302fc777fa403d438c95334dac43fc6f69b90f30ace0435ea0ebb2d078
3
  size 13498044
dqn-BreakoutNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518f87b03bdb44fe9d7be5db95a02500ec68241de33b25e2c0b8a5b7d06db0bc
3
  size 13497178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f565084fcc52b4c9caec5882228a84863f58101a6d0907d758df9fda342e02fd
3
  size 13497178
dqn-BreakoutNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
2
  - Python: 3.10.12
3
- - Stable-Baselines3: 2.2.0a9
4
- - PyTorch: 2.1.0+cu118
5
  - GPU Enabled: True
6
- - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
 
1
+ - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
  - Python: 3.10.12
3
+ - Stable-Baselines3: 2.1.0
4
+ - PyTorch: 2.2.1+cu121
5
  - GPU Enabled: True
6
+ - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c34c73a61e40d64c2a4e1496e04b710a15a3d7506d0ca2cfe90649442e79b22e
3
- size 72743
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c426c9a9cc6e55742562142ddc080f38ebce56f22ae3e865b43bed976ec2fc
3
+ size 72778
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 7.6, "std_reward": 3.8000000000000003, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-05T07:16:27.641249"}
 
1
+ {"mean_reward": 104.5, "std_reward": 45.47141959516989, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-14T13:50:20.373742"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae75b70630ea94b952f940814b524120f6acc40100457cc50d74dc37aca449f8
3
- size 47411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5579a530a30fc1732198ef4494531effd410b1fe66e42f7ab340687dc4368f88
3
+ size 50202