Hugging Face's logo

hlabedade
/
unit3_coursrl

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
hlabedade commited on
Commit
09d6652
·
1 Parent(s): 35cddfd

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 +4 -4
  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: 7.00 +/- 7.14
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),
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: 612.50 +/- 207.55
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
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 377281903
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2593077729
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000
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 sha256:6251d855408091a5ec3d9f461cd8c54f88a780afb7733e1fb6862e88ecd9f777
3
- size 13714999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ad0c23510b0e9b352083d78fd21855b1f3bfc1c85dd5d4674d809223c80e6f
3
+ size 27220210
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.2.0a11
 
1
+ 2.3.0a4
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 sha256:975088b3ac1fdbdab482fce5c017f84b9e1b2d5c291d1eedc9ca990284b434d0
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b94bcc8e8f3553f9bec3f27510022b404bc957c775b143197acdc01a72ed7cc
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350772db91198c2ceba5a2938318076d91a880e5296d9f0140f2c7d74e1c09df
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-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: 2.2.0a11
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: 2.3.0a4
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 sha256:48e7af439efb1028119e21ae2554ffd754e2a5336259ad55dc6ea536ad7a2331
3
- size 296919
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e2bca519571324ba8181c31b394253797c1214c37b33be9abb48992ab1f149
3
+ size 209287
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 7.0, "std_reward": 7.14142842854285, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-16T10:03:33.856536"}
 
1
+ {"mean_reward": 612.5, "std_reward": 207.54818717589416, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T11:01:08.620727"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1abeeb7f85852b2d4f7cca08a9979b6d91a7ca1c1f5c01d40fb10644d9e4632
3
- size 5741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911afddcd3d42ea63d46fe90ba6da1509f078a8e49dc25d3241ef6a4269fa97c
3
+ size 28196