Hugging Face's logo

JuanMa360
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
JuanMa360 commited on
Commit
ba29b67
•
1 Parent(s): 2450d48

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: 29.00 +/- 64.30
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: 401.00 +/- 210.32
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
- - 419482213
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 213883835
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
+ - 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:a02925c61ec4f3fc567c69c2f170a8acb04c92b5897c83037936dae8c200d2ea
3
- size 13714993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa1057c30399c7ddd8cd34a624fad5241ea89502ab5a7ddaac670cafa02ccd1
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 sha256:2e61564a059bc67193a95cd784758942199341e10ffcaef57e51009ae5a322c4
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:a58e5cca6472b98d609ee304275f2aa26cb8c333ffc3d5be7b09fb29de07a3d1
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a809ec3ccca23d552a7d21748b55a1b5506ab6cb2ab7ce1795e679c7baf79932
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:cae3de750f432875df42a4011aeedbc220ba38b313576b27b5dbc3ebf8a98d59
3
- size 294896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c459ec2e356586d8e8f46c6da2266409fa8e75339dc084c7c9a7fb2e96fa279
3
+ size 261461
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 29.0, "std_reward": 64.29618962271404, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-08T07:23:20.373233"}
 
1
+ {"mean_reward": 401.0, "std_reward": 210.3188056261256, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-24T05:47:51.350102"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4299569d3b4685c5b74c5ed3f0c312021433f3cf9c5d1c424821532dc73547a
3
- size 5970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e185ad18a863263a82627c976cee271d7343d17d03a0b0a5b6c5ce9f5c1f7db2
3
+ size 37013