Hugging Face's logo

bpugnaire
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
bpugnaire commited on
Commit
7439e5e
•
1 Parent(s): 09c8613

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +2 -2
  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: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 5.00 +/- 7.07
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 645.50 +/- 178.88
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 2000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 307137928
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 154689280
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:853345251e44b226d09b7fb7efa25a63458f9117a2c1d62aa59840e2d172f46f
3
- size 13714993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1b4fe03a13fc5dd7c9532922dc405e138621336f65888028e58ed27b5f953b
3
+ size 27220132
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3795634cbed16b60e17054a7a5c36872cbd74bb4c340dea2430821a563309bb0
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02417e313b769148422215bac37c7650ff38301b98193919715a77d935f8fb03
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0859cb5892e6bc1f47112cc8268d517a0e108c460b525de6abc12788f1b31f
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
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: 2.2.1
4
- - PyTorch: 2.1.0+cu118
5
  - GPU Enabled: True
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
 
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: 2.2.1
4
+ - PyTorch: 2.1.0+cu121
5
  - GPU Enabled: True
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db13127af1afff79a46340c2dcb1019924e473abb0fcb413073b8546932fd7c
3
- size 294075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acba1fb658fcd3c54154d4a48c1213e346b3e188d8d8b0701130fdc9c7c891b
3
+ size 220549
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-08T07:30:28.050243"}
 
1
+ {"mean_reward": 645.5, "std_reward": 178.87775155116412, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-20T22:40:40.884709"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ecadb9303287d7e90db82924a8c640369f2e620645bd91e05e3cf0750f49d31
3
- size 5738
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0557b15484d72b2a8edb66fc70f237f3a633a279c39df7722268dfae36b1292
3
+ size 65001