Hugging Face's logo

hyllius
/
SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
hyllius commited on
Commit
7b2ce0e
·
1 Parent(s): 86bd8ce

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: 499.50 +/- 51.60
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,10 +67,10 @@ OrderedDict([('batch_size', 128),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.02),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 549.50 +/- 203.01
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.05),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0002),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1538372460
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1443146148
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,13 +8,13 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.02
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.05
12
  - - frame_stack
13
  - 4
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 sha256:21b27645435d3e04e31bd856dbe1c7c444f05f898fc64cd966987eefca8d7bb8
3
  size 27218394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46c37e62da1040088d2ebe35e4c65623f50a53a1a48186b271d1286ab233be0
3
  size 27218394
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 sha256:712687aa2ad19ab2a122a8e45bc89f844a9e73adf5b0338493f052471e749789
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d159083ae573a0e170701663fd4fd6f42cf9651cc7e34996c1995db2339969
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a550b4130382cf6a2cf56f7355294814f90952022466cc76f315d45d4134be3
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dce8ea3ea13736c4ffabaaef443707ee03387380c1509694fbe6944cafa3832
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e468a56cbfda282c3dc337688bd5f1777ce07f400deb405fc5c915b397e86343
3
- size 234746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed705c2ab24a2913ec7b2dcedac85baa366db33df1d81007f85a2676a91f70c
3
+ size 239317
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 499.5, "std_reward": 51.59699603659112, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-12T05:20:12.529095"}
 
1
+ {"mean_reward": 549.5, "std_reward": 203.00800476828493, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-06-12T07:12:32.265883"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b6c495a7fc81b19e8e4d8677c8ec6e1f74e95b628244524a689bce502774436
3
- size 36351
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d4b4695953a8ee05e26176db4cf2df9629c32918c7a23e41bdd9b1cea95088
3
+ size 36914