Hugging Face's logo

crossroderick
/
qrdqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
crossroderick commited on
Commit
39bacd5
·
1 Parent(s): 360956b

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -5
  2. args.yml +1 -1
  3. config.yml +1 -7
  4. qrdqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. qrdqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. results.json +1 -1
  9. 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: 525.00 +/- 100.17
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,12 +70,9 @@ OrderedDict([('batch_size', 64),
70
  ('exploration_fraction', 0.03),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 'lin_0.001'),
74
- ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 1000),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 768.00 +/- 234.95
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.03),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('n_timesteps', 3000000),
 
 
74
  ('optimize_memory_usage', False),
75
  ('policy', 'CnnPolicy'),
 
76
  ('train_freq', 4),
77
  ('normalize', False)])
78
  ```
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3744970726
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3784741123
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -13,17 +13,11 @@
13
  - 4
14
  - - gradient_steps
15
  - 1
16
- - - learning_rate
17
- - lin_0.001
18
- - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
- - - target_update_interval
27
- - 1000
28
  - - train_freq
29
  - 4
 
13
  - 4
14
  - - gradient_steps
15
  - 1
 
 
 
 
16
  - - n_timesteps
17
+ - 3000000
18
  - - optimize_memory_usage
19
  - false
20
  - - policy
21
  - CnnPolicy
 
 
22
  - - train_freq
23
  - 4
qrdqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c12de9584fe1a68cac977d50eda90d46f3d814c3824823ff3e1719fd50c07a4
3
- size 37020426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06641b7f1c631d9de09fbb681df8b82509910e41228b3c08fa868332b8ce327a
3
+ size 37018978
qrdqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3f02a7e02d8281744bb304d3093a4416dad731042d8945df3b30a96b3bc51ef
3
  size 18405963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823c1018f77306c1b5e6a7d593d9a886384ca515fdebbb6896a78af593ebae8b
3
  size 18405963
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:380a74be666999783ef56bfff64f8ea4791bc945f7d24820600535fc0c16609d
3
  size 18405545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b99307c4b59f7bd8f15176d2b902fc4766006a1b56035ad76e8c7b0bddcfbb
3
  size 18405545
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 525.0, "std_reward": 100.174847142384, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-25T18:00:13.079884"}
 
1
+ {"mean_reward": 768.0, "std_reward": 234.94893062110327, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:17:38.271632"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f01b73b4e55db5656e53580a9a2783092d75fcf4da04e222a72e20b3b4e42ca
3
- size 35918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deaa16ec36c55e7fd56ba15b9a34e13fb1117f63bad583321b92ff2c8ad33011
3
+ size 102368