Hugging Face's logo

Krazeder
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
Krazeder commited on
Commit
54a5baa
·
verified ·
1 Parent(s): 7c2034d

Initial commit

Browse files
Files changed (10) 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 +4 -5
  9. results.json +1 -1
  10. 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: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 100000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 583.50 +/- 50.50
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2450294149
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2752691242
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:cde3b3ebb3fc05ce3a0eaf4983b611f159ae3a6e7b5666a8131744ce80c1a422
3
- size 13715962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc1b88099bfd1b5c5ad3c81a6cbcab4b5bffae0ccf0b0834ebc4fd613fefd7a
3
+ size 27221897
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39fce7e093b1d71314c3b30ed83142432c449cb9349cd68a77776a7e82c05418
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:912ddd594be12ea7cfca868c1f8154883e754ea0908032fe8d17e9abab0f5555
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e516898bec22c3a4bd1a3fe4b87d992bdf012f2baa224af59f585730e1b3dc6
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,8 @@
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: 3.11.11
3
  - Stable-Baselines3: 2.5.0
4
- - PyTorch: 2.5.1+cu124
5
  - GPU Enabled: True
6
- - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.0.0
9
- - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-6.8.0-54-generic-x86_64-with-glibc2.39 # 56-Ubuntu SMP PREEMPT_DYNAMIC Sat Feb 8 00:37:57 UTC 2025
2
+ - Python: 3.12.3
3
  - Stable-Baselines3: 2.5.0
4
+ - PyTorch: 2.6.0+cu124
5
  - GPU Enabled: True
6
+ - Numpy: 2.2.3
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.0.0
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T21:18:15.269559"}
 
1
+ {"mean_reward": 583.5, "std_reward": 50.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T23:28:31.356723"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1776065fcd1564e67fb2c39fcf3e67f9e2ea69fbc13889b86974fa98b0f8e99
3
- size 5814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7bfcf477917111e4251be86e436dcfc04915b967ec48fb27e19cb7c0a59a03
3
+ size 36165