vk21 commited on
Commit
ffb15ab
1 Parent(s): 854afe3

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 181.00 +/- 112.29
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,15 +62,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 16),
66
- ('buffer_size', 52000),
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', 1e-05),
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: 576.50 +/- 174.97
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
+ ('buffer_size', 120000),
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', 7e-05),
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
- - 3726713782
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3915396317
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 16
4
  - - buffer_size
5
- - 52000
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
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
+ - 120000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 7.0e-05
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:ff9d5a59b7306191c4f403098576106a1a7c0abe4ca03c53b56e134a410d0d3f
3
- size 27224807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d22b554c8d6878ea81eeb2355de62da00b8a8c8a2277442c586bc81c78e0bfc
3
+ size 27224808
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 sha256:301b4a9f647eedc1b2033d0aad90ac1148424b0c6466ecf78937da2858978996
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce2588057bf6658aea8c36ead408ceecbf6dabac12d691cac22ea50608a1c89
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:dcd9abd03ac9dbabcc0be81b386c0893cba0ad7493ad187e621fa2a5f3a1ad4e
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a7485968e0421854ca7f75c4a824865ae16da926cc78e6c0d610cc05f3c08b
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:119a7f723f668c9445cd8ae5c393894a444671e32f5730e836e64ef8cafeb079
3
- size 203109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efcb46a8589e3687157e85acacd63f6112343367bdc62efd2a6d050e07d96fe3
3
+ size 211923
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 181.0, "std_reward": 112.2898036332774, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T12:44:43.962907"}
 
1
+ {"mean_reward": 576.5, "std_reward": 174.97214063958867, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T14:27:18.443323"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bbf927ba4b145ec876a0fd32079124dc36c98192ac74358b3e07eabebe38fc9
3
- size 43846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1228e924db148bd14f0bde8067aee3d681de1e647c8604154e6f65e930f1e7f1
3
+ size 37046