Hugging Face's logo

DumbleDuck
/
ddqn-SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
DumbleDuck commited on
Commit
6f2b9c0
·
verified ·
1 Parent(s): ff5568e

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 +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  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: 268.50 +/- 78.17
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: 343.00 +/- 200.65
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
- - 1218526354
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 430431765
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 sha256:3bec9d67ea3836e30026fe0896aa467bdaa113bdd56adcef6a0573527b0ca802
3
- size 13716399
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75592df03d526609b4623598d8f8c38966a34349ae31c33a2531d1a2b4c326b9
3
+ size 27221652
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 sha256:910e15b05c806b3f267d27fd926d7516c88e4e29106613e5ec61caeb16ebea1e
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3abd8fac9f24d6dcd1664cfab3a07f0b4e67f34e44b684c9e8e443b50af75562
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a333059c752a80812a1131a74454b6341b279df0dc9a364ba007123a8f24d68
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.11.12
3
  - Stable-Baselines3: 2.6.0
4
  - PyTorch: 2.6.0+cu124
5
- - GPU Enabled: False
6
  - Numpy: 2.0.2
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
 
2
  - Python: 3.11.12
3
  - Stable-Baselines3: 2.6.0
4
  - PyTorch: 2.6.0+cu124
5
+ - GPU Enabled: True
6
  - Numpy: 2.0.2
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-18T20:33:37.841116"}
 
1
+ {"mean_reward": 343.0, "std_reward": 200.65143906785218, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-02T13:31:42.566043"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e93fcd5de881a3f65138442eedd3f453f2eb40194873ac619b5fe984dfde9985
3
- size 5748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a50e9dd2f42c8845576b32ebb9bd9ffabb836805d699a3096bdc272f29c5dd7
3
+ size 8260