Hugging Face's logo

Hevagog
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Hevagog commited on
Commit
6725f0b
·
1 Parent(s): 859bfac

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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. 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: 505.50 +/- 90.54
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,13 +62,13 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.1),
71
- ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 532.50 +/- 197.07
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.2),
71
+ ('frame_stack', 8),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 114512309
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1059522745
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -8,9 +8,9 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
- - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
+ - 8
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b889381cf46b159164abf7e854c413c8ff31b4d8d6fbd69737eaf3dc9bc0a12
3
- size 27220927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327a632565560b9f0bbcd17b136bb0e3ffa2ddd3d5ff4071c855136f71eb5c9c
3
+ size 27542011
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 sha256:530094c433981975fb5a3b84ca9b74c97a25b1dc1d9b375ac33b952c4e584eea
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f66aa87edc270ae97a51a0b0cd84272cdefa7c5029d5da3b696c7a81afff1a9
3
+ size 13571772
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b58b073635015d497ee10d10f5d62273d215ef2d11396e3e653c98a4e9beff6d
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc65d592d4913cfec7817717ea96a4ad12dfd65d8ad41684be7de038ac6468a
3
+ size 13570906
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 505.5, "std_reward": 90.5386657732485, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T23:22:14.095465"}
 
1
+ {"mean_reward": 532.5, "std_reward": 197.06915030009137, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T00:37:55.036527"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5707167a26848a50d5b2bb2e2ea6d7a448cbf8b5fe8d5f7aec93261068f7ff8f
3
- size 36143
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e78a781f9c178d9bbe737fd648e7da0df1c4c0c9e97519e94dc56e4c78efc2
3
+ size 33845