Hugging Face's logo

shahafw
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
shahafw commited on
Commit
c183de3
•
1 Parent(s): 5dcee2f

Initial commit

Browse files
Files changed (12) 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/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 6.50 +/- 10.74
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', 5000),
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: 602.50 +/- 113.83
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
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
- - 2858702794
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3348153180
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 5000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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 sha256:9973aab7713467b2dfac77024ddae0d079411a5107e0aba8801e90a2a8ff81a2
3
- size 13709520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a46c9e8d3a7be29fb0046c0adeb5b8ed220e0db8cdb2b49ee57313cece0704
3
+ size 27218399
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.0.0a10
 
1
+ 2.0.0a13
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 sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80d91a8737072c0f25c8c9b3beb9095ebe9fa7a66d5c74854fb75b99da9e5f4
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db7b6bf05cee67dc66fc7a184669ac4f8d82c50fe03beaa51e17268460f5930f
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b176f7c2d72962c890ce192f0a5d2c6caca6af5ff41ad8fe05b7ad5f1911c068
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  - OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
2
  - Python: 3.10.11
3
- - Stable-Baselines3: 2.0.0a10
4
  - PyTorch: 2.0.1+cu118
5
  - GPU Enabled: True
6
  - Numpy: 1.22.4
 
1
  - OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
2
  - Python: 3.10.11
3
+ - Stable-Baselines3: 2.0.0a13
4
  - PyTorch: 2.0.1+cu118
5
  - GPU Enabled: True
6
  - Numpy: 1.22.4
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9592f7bcd308cbcde0c96c0fa5e1260ce1249f9ef78ab62c82a93fd76d7725b
3
- size 291883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f99fbe7c39b8ffd8c0576dad37a026a671437060930ae81ee52caaa9789468
3
+ size 224727
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.5, "std_reward": 10.735455276791944, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-06T22:04:14.902519"}
 
1
+ {"mean_reward": 602.5, "std_reward": 113.8255243783221, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-07T20:11:42.286959"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a915b182bad3952eb8c7266fd58cf0fd5310f3a9e9cbfa2c6f4676bee3175fd7
3
- size 375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96724199bb29b1e1086c9c0105539c510607c3ea5e95a3f3bb6c53ba52f8ce67
3
+ size 59326