Hugging Face's logo

DumbleDuck
/
ddqn-SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
DumbleDuck commited on
Commit
3ec39e3
·
verified ·
1 Parent(s): 894630e

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 +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  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: 343.00 +/- 200.65
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,15 +63,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 32),
67
- ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
- ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 623.00 +/- 188.40
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 64),
67
+ ('buffer_size', 150000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.0002),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 430431765
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3447120685
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 150000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
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:fcc33c8afa1248a64f5bef54a3919346a66f41705583b1fa21bfe21b98588f42
3
- size 27221652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098e97c657b8e3f86073dc9bcf99c085763d1d52fb5d675ca4e1a61881b92951
3
+ size 27221651
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 sha256:910e15b05c806b3f267d27fd926d7516c88e4e29106613e5ec61caeb16ebea1e
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32abff60cfafce5435dde86e508ed2c09f858a992698229f086b78a7fe0bbe7
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a333059c752a80812a1131a74454b6341b279df0dc9a364ba007123a8f24d68
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca230886ca9905332ad9ea6ef88410a425242e57c2968440fc8a847d3cbc574b
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 343.0, "std_reward": 200.65143906785218, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-02T13:35:58.664048"}
 
1
+ {"mean_reward": 623.0, "std_reward": 188.403821617291, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-02T14:55:43.986844"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a50e9dd2f42c8845576b32ebb9bd9ffabb836805d699a3096bdc272f29c5dd7
3
- size 8260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084e9aee2c9d818a87bc9487267d04e0726555677045e546b37a5b0a85d178a4
3
+ size 32886