Hugging Face's logo

FBM
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
FBM commited on
Commit
83c2601
·
1 Parent(s): ccc7dfd

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 +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. 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: 744.00 +/- 203.95
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,9 +63,9 @@ OrderedDict([('batch_size', 32),
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
  ('exploration_fraction', 0.1),
66
- ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 525.50 +/- 101.11
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
  ('exploration_fraction', 0.1),
66
+ ('frame_stack', 5),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0002),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1549504425
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1147278394
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -10,11 +10,11 @@
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
13
- - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
13
+ - 5
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0002
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:a551c075bd4d2259f425329d8fadc48374d320743ae0282e7fdf5987e6ffcd14
3
- size 27224794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca42d9b4be1ec9805207f0f7cf32b8ce618cbb81bc7e6b7ccf49e3f32718071
3
+ size 27305518
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 sha256:2fbd021e5fb078e358f2a1df69735238a7b663297d37b1cdabdcc8cefdf61184
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f91d9ab7b060ada6d971a5137651ad7dab3826bd2f54cbbe0a8ca0231e5d74
3
+ size 13522123
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:702d96507b1fa116697a2faa4e51fdde5dc88366614809211b2faf2a83978e67
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801028f2c750fef62bcb4974bfa284eaee2ca45cb30280bf6c026ae3448f8abe
3
+ size 13521321
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10222ef4712bc131b062c8c48f8828b41e6a7f8c52d2a365e07ff669ee8db187
3
- size 235514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fd1326b74addfa4e0d179c9099cc37270010cb11d57b1ac24d16b2fa797f57
3
+ size 195450
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 744.0, "std_reward": 203.94607130317564, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T13:08:38.901863"}
 
1
+ {"mean_reward": 525.5, "std_reward": 101.10514329152598, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T15:25:01.620697"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f3ba390e89092dcaae3dbd213b751223eda85287daa04e9fd3ff9860127cb71
3
- size 63602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a1b5629a50075f09d181f3328ac5f2e15e3561413f051d228694cd08c68c4d
3
+ size 64232