hivex-research
/

hivex-WFC-PPO-baseline-task-1-pattern-0

Reinforcement Learning

hivex-wind-farm-control

multi-agent-reinforcement-learning

Model card Files Files and versions Metrics Training metrics Community

philippds commited on Aug 28, 2024

Commit

5089879

·

verified ·

1 Parent(s): 69eeb48

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,11 +18,11 @@ model-index:
       type: hivex-wind-farm-control
     metrics:
     - type: avoid_damage_reward
-      value: 4826.756228027344
       name: "Avoid Damage Reward"
       verified: true
     - type: cumulative_reward
-      value: 4826.6553881835935
       name: "Cumulative Reward"
       verified: true
 ---

       type: hivex-wind-farm-control
     metrics:
     - type: avoid_damage_reward
+      value: 4826.756228027344 +/- 36.95591548454739
       name: "Avoid Damage Reward"
       verified: true
     - type: cumulative_reward
+      value: 4826.6553881835935 +/- 33.99286534404727
       name: "Cumulative Reward"
       verified: true
 ---