Hugging Face's logo

erdody
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
erdody commited on
Commit
b5aa35e
·
verified ·
1 Parent(s): d07ef27

Initial commit

Browse files
Files changed (10) 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 +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +0 -0
  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: 162.50 +/- 179.04
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -66,13 +66,13 @@ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 300000),
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', 0.0002),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 700000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 490.00 +/- 78.61
20
  name: mean_reward
21
  verified: false
22
  ---
 
66
  ('buffer_size', 300000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.05),
70
+ ('exploration_fraction', 0.01),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0002),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 4227826200
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1017346272
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -6,9 +6,9 @@
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 700000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.05
10
  - - exploration_fraction
11
+ - 0.01
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57e866785be5714cfb6a64e91a7b5c25d952ff2dac7c2357e0493116ef075560
3
- size 27220880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8df281880dee9b7f1d1b04205e1cd4764b3af1041aa3754791ea2bba01ca07
3
+ size 27220889
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 sha256:78b0617708f6668736b248b96623fd9f8b9151caad7bd551927a7f9a34c13989
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59f81d315efc2a0c58d2ef1121248d91122f494c32ec3c6c5833f7a56972ccb
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d476c36719cd90d8f7087ffa4598a26a418d91437b57449a1d0eb9f1440567b4
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08404221924ec23e70f19e7b793db42d5ab53310b9d2006984e3211697ebca0a
3
  size 13505370
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 162.5, "std_reward": 179.04259269793877, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-01T00:32:49.048182"}
 
1
+ {"mean_reward": 490.0, "std_reward": 78.61297602813418, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-01T23:24:21.605664"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d73f350a024a6e47602923b6ababa8ca9da1b94f0d18e925678fbfce7d109b5
3
- size 23349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61049337f2057c675cd75c67120059c42aa254751fbe24a1bace80307a9e8f2f
3
+ size 295801