colinrgodsey commited on
Commit
3878a7e
·
verified ·
1 Parent(s): 3a260d8

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: HealthGatheringSupreme-v1
18
  metrics:
19
  - type: mean_reward
20
- value: 0.25 +/- 0.51
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -32,7 +32,7 @@ model-index:
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
  'recurrence': 16
 
17
  type: HealthGatheringSupreme-v1
18
  metrics:
19
  - type: mean_reward
20
+ value: 14.87 +/- 10.43
21
  name: mean_reward
22
  verified: false
23
  ---
 
32
  'learning_rate': 0.0005
33
  'learning_rate_min': 1e-06
34
  'gamma': 0.99
35
+ 'gae_lambda': 0.99
36
  'clip_coef': 0.2
37
  'total_timesteps': 2000000
38
  'recurrence': 16
logs/events.out.tfevents.1722001744.tf-notebook-0.66842.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a9b8355ea7dd645a64b3ae6e052e7ce55a4d00c7c267d2e350e359e2979bd5
3
+ size 433947
logs/events.out.tfevents.1722002228.tf-notebook-0.67002.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d040b88df6f58d3237395055a354c86d4d4d0d17169b451c8cd03f33d6ab7d8
3
+ size 1202971
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ddb4102a7359402db380e0fb13b92f4db1070d7c1cdf92086072aec56d2cc1a
3
  size 16108110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5918372a80112df104991af0ffe824801448a7fb544e17dbd2c0c1a71129791d
3
  size 16108110
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ee072178f347c72278c06ccf57c087256d4faf7d29687727a06c6566b818922
3
- size 15653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492504db6f6e4e6f4360740fb1337fee37392ff67bd4841d8d247e93cb0943fc
3
+ size 62297
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "HealthGatheringSupreme-v1", "mean_reward": 0.2476000040769577, "std_reward": 0.5117013454437256, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T03:58:27.613666"}
 
1
+ {"env_id": "HealthGatheringSupreme-v1", "mean_reward": 14.868197441101074, "std_reward": 10.425899505615234, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T14:20:09.596163"}