Hugging Face's logo

DanielDsouza
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
DanielDsouza commited on
Commit
5f44da7
•
1 Parent(s): cb2783b

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +4 -4
  3. config.yml +1 -1
  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: 239.00 +/- 181.66
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 500000.0),
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: 648.50 +/- 112.87
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
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
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yml
6
  - - device
7
  - auto
8
  - - env
@@ -32,7 +32,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - -1
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3865511864
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - ''
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - null
6
  - - device
7
  - auto
8
  - - env
 
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
+ - 1000000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4286256228
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - /content/logs/dqn/SpaceInvadersNoFrameskip-v4_1/rl_model_500000_steps.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
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:bc3ddd65664719984950e4672fe466e160be906124d6862ed65afd70d7eb51da
3
- size 27220129
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0be8019f9d310f80013f080fb09823c7aa05d81acbf1fd0586c465b1a76c12e
3
+ size 27220132
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 sha256:70287cde46d7e09436da7c39b8b390e2066792591ff89448c56fc323c11e4dbe
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6e5dfa6a52c13c1b9f4bddf1213cec2adf68a938203936cdbd1a020640b630
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bc7bf4f2e9145c63560e0de869ef0e4a54ea9cc76a959bd01da28f70de12dac
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879ec7170ef3afd9723e249485eb5386b6b7533a8ff8a2f7af1e1b845fcf4f64
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e04a9e34e6e3a9777c8635d651f38f0df320aa4f2e1764f44cdfabfd0a6a847f
3
- size 265477
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e4b9ad9ea796608a386acd9ead738277c7b53e70f256451257278ab74bf2d7
3
+ size 199097
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 239.0, "std_reward": 181.65626881558478, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T10:27:20.154271"}
 
1
+ {"mean_reward": 648.5, "std_reward": 112.8727159237342, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T11:59:07.325572"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:635a724501f10027034d0ec279afb11f2a769eb4d36a4e1bca6244bc06dcb9e6
3
- size 21846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9eb3e8e6474670be173f1fe75e65bb4604fbf961ddfa51d5abbab6f96bc926
3
+ size 30160