Hugging Face's logo

dfomin
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
dfomin commited on
Commit
c773ce4
·
1 Parent(s): 6f22bdf

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +2 -2
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 719.00 +/- 299.68
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', 10000000.0),
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: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1.0),
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
- - 3889340253
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3462587383
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1.0
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 sha256:6f0089c35ef8357e820e8b33fcdadf35197a40cf1e1c8a646e4cb57f3780ab8c
3
- size 27218401
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e77a7ad1b8018c8d3f7bac691bae3b92488ee87433f334e49174deddbac6c9
3
+ size 13709163
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 sha256:3c7dcdd8ff174dfcced160e2f4e9803ecd2043af5715f02a1aab157d5e21b0da
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
+ size 687
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f71b7c09db90da7950e502aa24f9fe7f13176d4e2c274ab0b592e8e5edd72e30
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c775c0faee292c5adcf507311d88f568aa98933a4780f959d72f8ac20757f406
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,5 +1,5 @@
1
- - OS: Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
2
- - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu118
5
  - GPU Enabled: True
 
1
+ - OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
2
+ - Python: 3.10.6
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu118
5
  - GPU Enabled: True
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0b275c5ce980b9af9092e8d6f56eda9f6b880433b958e3622598f33e6038fd3
3
- size 270591
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961ab6016871f866ed78c92d21ef7930dec0110e72144703e0be2b439e42e1af
3
+ size 267942
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 719.0, "std_reward": 299.68149759369527, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-15T18:38:50.521594"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T12:47:05.211270"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ecf22f49b062d18e594199f72f086f117a2564a6824205310dd9022353ea02e
3
- size 45669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b780a2a0f551a02bcac43f5c5e7d29e7fac9630331e910db7cdd5ccc7594312
3
+ size 205