Hugging Face's logo

MartinVanBuren
/
unit3a

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
MartinVanBuren commited on
Commit
94c1593
•
1 Parent(s): 22a1283

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 +1 -1
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +0 -0
  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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,7 +70,7 @@ OrderedDict([('batch_size', 64),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1422901342
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3372744155
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125c56ce06dfe205ab421cbce5fe37ef8934a1cfcaa857bd9207d34f40e0d414
3
  size 13715666
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5883574860751bfa1428afdb2b4acd0b0f8a93a00eeaddac55b979801670a95a
3
  size 13715666
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 sha256:9ebba6ecb40924ab5e69c1644febc657308bd2e400895c9595ed25c1fe6cbe34
3
  size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6edbbd4dee9da7ffd9281eab551b9fab84618d9675b119ccd2183c012f9ed33b
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4faf8d68604d8eca5a382b13c8b6996358a530642ed38b0fb12613b256fdb4e2
3
  size 13505370
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-02T16:58:01.103533"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-02T17:04:26.382450"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:274c5636a12c335e341324c4799b15c51826c782fb2548068c0d590106e7452d
3
- size 5585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8562a09d6a1742f76b6722f2aece14ff5d3d0afb128f927aa782a6283c834c77
3
+ size 5731