Hugging Face's logo

numan966
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
numan966 commited on
Commit
6086c46
•
1 Parent(s): d450db2

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 +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: 618.00 +/- 169.87
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 64),
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', 4000000.0),
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: 687.00 +/- 375.37
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 3000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 622850569
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 680832506
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0002
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 4000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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:d47ab517db617804421d549c3b14657c904e3c1cd805374fe784dd3368749667
3
- size 27224804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9aae3951810e4666dca4f6bc72227bec9a3b1d359a1c3c80dd865033996c9ff
3
+ size 27224803
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 sha256:2a98d3a3072746ac3fa80d8fdc57f17fb41016734bd0e87b22eb71a4b84c08b9
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19981498aa98a56e452dbb6fad6967dec796337930af42576f6a36b44499eb6b
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23e1c5ebc3dd2dc82e06d04bacb1ae9db3cf1eae430b18afd316e0a5701d32df
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de920ab4c030cf67a341f318b115a79b4afac0b3c99c832615cae96facc77b7
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad65afe471cb8e3471da591346c2793dc483889c167c6c88817fb0f354bb932f
3
- size 197802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60328c440c5abdc328bee99be56cab84d65f043ad86089f9d7d8b1f41f7c0f0
3
+ size 181723
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 618.0, "std_reward": 169.8705389406886, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-20T21:01:26.228474"}
 
1
+ {"mean_reward": 687.0, "std_reward": 375.3678196116444, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-21T22:17:50.939825"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b71532eff206c3f7d52323ccb45c6a5718626dbcc2e4eb389b1566bee620e5e8
3
- size 122900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95db4c04f94e896b1904250bfa04fe7e9abde3a6cd36791ee3bcd70cb5017b5f
3
+ size 90218