Hugging Face's logo

colinrgodsey
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
HealthGatheringSupreme-v1
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files Metrics Community
colinrgodsey commited on
Commit
e020ca5
·
verified ·
1 Parent(s): 8544a15

Push agent to the Hub

Browse files
Files changed (18) hide show
  1. README.md +12 -11
  2. logs/events.out.tfevents.1721869554.tf-notebook-0.8669.1 +3 -0
  3. logs/events.out.tfevents.1721869582.tf-notebook-0.8669.2 +3 -0
  4. logs/events.out.tfevents.1721870482.tf-notebook-0.8669.3 +3 -0
  5. logs/events.out.tfevents.1721870495.tf-notebook-0.10474.0 +3 -0
  6. logs/events.out.tfevents.1721870528.tf-notebook-0.10474.1 +3 -0
  7. logs/events.out.tfevents.1721870553.tf-notebook-0.10474.2 +3 -0
  8. logs/events.out.tfevents.1721870563.tf-notebook-0.10830.0 +3 -0
  9. logs/events.out.tfevents.1721870604.tf-notebook-0.10989.0 +3 -0
  10. logs/events.out.tfevents.1721870771.tf-notebook-0.11148.0 +3 -0
  11. logs/events.out.tfevents.1721870852.tf-notebook-0.11323.0 +3 -0
  12. logs/events.out.tfevents.1721872526.tf-notebook-0.11499.0 +3 -0
  13. logs/events.out.tfevents.1721872613.tf-notebook-0.11896.0 +3 -0
  14. logs/events.out.tfevents.1721872749.tf-notebook-0.12294.0 +3 -0
  15. logs/events.out.tfevents.1721872878.tf-notebook-0.12294.1 +3 -0
  16. model.pt +2 -2
  17. replay.mp4 +2 -2
  18. results.json +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  tags:
3
- - doom_health_gathering_supreme
4
  - ppo
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
@@ -13,32 +13,33 @@ model-index:
13
  type: reinforcement-learning
14
  name: reinforcement-learning
15
  dataset:
16
- name: doom_health_gathering_supreme
17
- type: doom_health_gathering_supreme
18
  metrics:
19
  - type: mean_reward
20
- value: 23.32 +/- 12.86
21
  name: mean_reward
22
  verified: false
23
  ---
24
 
25
- # PPO Agent Playing doom_health_gathering_supreme
26
 
27
- This is a trained model of a PPO agent playing doom_health_gathering_supreme.
28
 
29
  # Hyperparameters
30
  ```python
31
- {'env_id': 'doom_health_gathering_supreme'
32
- 'learning_rate': 0.001
 
33
  'gamma': 0.99
34
  'gae_lambda': 0.95
35
  'clip_coef': 0.2
36
- 'total_timesteps': 1000000
37
- 'ent_coef': 0.001
38
  'vf_coef': 0.5
39
  'max_grad_norm': 4.0
40
  'epsilon': 0
41
- 'num_minibatches': 2
42
  'update_epochs': 1}
43
  ```
44
 
 
1
  ---
2
  tags:
3
+ - HealthGatheringSupreme-v1
4
  - ppo
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
 
13
  type: reinforcement-learning
14
  name: reinforcement-learning
15
  dataset:
16
+ name: HealthGatheringSupreme-v1
17
+ type: HealthGatheringSupreme-v1
18
  metrics:
19
  - type: mean_reward
20
+ value: 23.42 +/- 20.23
21
  name: mean_reward
22
  verified: false
23
  ---
24
 
25
+ # PPO Agent Playing HealthGatheringSupreme-v1
26
 
27
+ This is a trained model of a PPO agent playing HealthGatheringSupreme-v1.
28
 
29
  # Hyperparameters
30
  ```python
31
+ {'env_id': 'HealthGatheringSupreme-v1'
32
+ 'learning_rate': 0.0005
33
+ 'learning_rate_min': 1e-06
34
  'gamma': 0.99
35
  'gae_lambda': 0.95
36
  'clip_coef': 0.2
37
+ 'total_timesteps': 2000000
38
+ 'ent_coef': 0.05
39
  'vf_coef': 0.5
40
  'max_grad_norm': 4.0
41
  'epsilon': 0
42
+ 'num_minibatches': 4
43
  'update_epochs': 1}
44
  ```
45
 
logs/events.out.tfevents.1721869554.tf-notebook-0.8669.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6947fbbf2fff5fed1c0e049c1a6c69ea6720ba1a4ed7b01fe025d0fc61864a2a
3
+ size 5555
logs/events.out.tfevents.1721869582.tf-notebook-0.8669.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704bd63940b8708968784f9423a173cc46aafe172f6eed3ef20d40d2cb7f4fff
3
+ size 263043
logs/events.out.tfevents.1721870482.tf-notebook-0.8669.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9248687fc0867b83fc4edf497c02d8f8541c504eea38338f2530abc775ae69
3
+ size 88
logs/events.out.tfevents.1721870495.tf-notebook-0.10474.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba644caa7a3a79265839058cd7bbb1a21dc08ca4f66b8f861b3aa41ad1fe1df
3
+ size 88
logs/events.out.tfevents.1721870528.tf-notebook-0.10474.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86cb3cbad2ae86756572dd6a5ab1af46f565751b14510ced7c1e0fa8b2a5727c
3
+ size 88
logs/events.out.tfevents.1721870553.tf-notebook-0.10474.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4f8252a59cf1bc6dbc44aaad64de896962c2532002f6ea40d0e691ae8e3d0d
3
+ size 88
logs/events.out.tfevents.1721870563.tf-notebook-0.10830.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd7e66684e4eb33956cc55dad18f0cfccc10d6f5ba2c84fff9a4ad43b26b894
3
+ size 88
logs/events.out.tfevents.1721870604.tf-notebook-0.10989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00812c9c3b7b250243f82f95379c56074a7c06344133a950aef20a9769a58b6c
3
+ size 88
logs/events.out.tfevents.1721870771.tf-notebook-0.11148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccd4023cb6b778bde58abd7957e2813477ae8e89bb834468942efeb3d7a5fd5
3
+ size 8280
logs/events.out.tfevents.1721870852.tf-notebook-0.11323.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adec6207f5b7601cc34663cd81a67970db0c813c7bab52fe477b30a7d00acb60
3
+ size 492195
logs/events.out.tfevents.1721872526.tf-notebook-0.11499.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926b0a2823d32f53977ab71f81b06c4a462808f7a05f958dccadf3fe43853252
3
+ size 8280
logs/events.out.tfevents.1721872613.tf-notebook-0.11896.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096341e46438d876a38a4d3925927d07fb5bb78f2d0f7fc59f2e05f70aea7c23
3
+ size 24664
logs/events.out.tfevents.1721872749.tf-notebook-0.12294.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50c813ab17f7374742923890098bbb2638152a2800ac9ee1d8016cb39e1390c
3
+ size 88
logs/events.out.tfevents.1721872878.tf-notebook-0.12294.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110886d5926cde26685bb5291066ec5c7a2ecd593edac5c18854a70c0266f3e3
3
+ size 601227
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ac57c7a562674be7b647e77c7397eeb4049ab42bbfb65ecd8c400e8a57a6af8
3
- size 16208178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f422fd65107d4b849ee465442c8d2cd7e559f763626598965f355384a94db3
3
+ size 16091362
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:096d2848cacb8d6b3fea66adf12b653f332423a7d8c7dbf1d353da4c1493bbf0
3
- size 10432852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8e6ba71ad9ef373f72deb5744cdd952f78c1cb3a173ca8f05a518e49b50a9e
3
+ size 7298703
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "doom_health_gathering_supreme", "mean_reward": 23.317407608032227, "std_reward": 12.858668327331543, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-25T01:02:59.758995"}
 
1
+ {"env_id": "HealthGatheringSupreme-v1", "mean_reward": 23.419818878173828, "std_reward": 20.225461959838867, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-25T02:42:47.105650"}