Hugging Face's logo

paulaolmedo
/
dqn-SpaceInvadersNoFrameskip-v4__

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
paulaolmedo commited on
Commit
658ecc9
•
1 Parent(s): 5733d8d

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: 414.50 +/- 142.42
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 4147398911
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3606724673
60
  - - storage
61
  - null
62
  - - 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
+ - 1000000.0
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 sha256:94592e5959504bf278f2b78af23ae5e294fe13228c5d6d9fd4b12f0d403260dd
3
- size 13715667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3aae8eee1aada433289c0194b8af53f9b97e16245a94bcc71e9683d368c758a
3
+ size 27220792
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:e30bb8d893dbe5834d5e8dd0cddeb84dce43a8b1a8c202dc1fe53414cdb2ebfd
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:aabb6151f4b837b2877a98a51d9a44724ee2c6d260584dd53469e53698e18359
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e496405fb6bfcb804babb2418a051575b80173417a2ebc6b989ca9e335da47
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,4 +1,4 @@
1
- - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Tue Jun 18 14:18:04 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a4
4
  - PyTorch: 2.3.0+cu121
@@ -6,4 +6,4 @@
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
- - OpenAI Gym: 0.26.2
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a4
4
  - PyTorch: 2.3.0+cu121
 
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.25.2
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 sha256:0e7f73be7307fc20c2daeb4dcc499a174231a34b50558360a55ecbd20b0b2923
3
+ size 229543
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-02T14:53:23.982143"}
 
1
+ {"mean_reward": 414.5, "std_reward": 142.41576457681924, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T14:47:50.975639"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c062be74982db200f0cd05aab6bbaa4ffc0a4c7a6ee6993cbbc6f8cff170b73
3
- size 5746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e63a0d987b3488e526c07c93870a16f346f2b59634afe01180e7d680eea580a
3
+ size 36261