Hugging Face's logo

tomaszkowalski
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
tomaszkowalski commited on
Commit
83dbb0d
·
1 Parent(s): 6ea3e22

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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 +2 -2
  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: 563.50 +/- 140.48
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,12 +62,12 @@ 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),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 658.50 +/- 231.66
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', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1346172528
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3713672271
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
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
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
  - 4
14
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4fed5ccad11352ebf304e79472b82af06f2e4818b9f80a4263b0ebfa3bea047
3
  size 27220788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b04a5fca51f0b1e0fb32bad9e90f4e09524319e01ee47eed57083beec1fad5
3
  size 27220788
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 sha256:84ec1c281bcbe296e3d813aa1d191b8e5108819e382bf5d5362d53ab721c35ee
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a79deb758925110cfd47a6e2a0ed5f84b95304256d0d54777301473175256c1
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:fe12164ca9b48c0a34adbab9e462b2d1fcefb6ac21a060ba6a375f04d2970f58
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9adbe01320bb341698ccae26b07323295d36749b48f10da480cbb0f9c737a220
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58cb6ca6d4af2a1a25bdb349c89d454cb113bd11b706d13cae4ca04e79cb258f
3
- size 223579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e39468a2ae4df5dec113926ba1d5b1734440b3da6c57bea74fc060e5b2947a
3
+ size 235475
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 563.5, "std_reward": 140.48220527881816, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-06T21:40:37.000829"}
 
1
+ {"mean_reward": 658.5, "std_reward": 231.65761373199027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-06T23:18:53.131788"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f6e9a2af1c0a13f6cd7560a1efaa6b4adc5dd338f0d5bee95dc522640bcdab2
3
- size 36790
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f6077c998adee5300edfaa9c739196bd90580ab7ced82c9b993936ea34c198
3
+ size 35823