Browsing Division of Electrical, Electronics, and Computer Science (EECS) by Advisor "Kolathaya, Shishir N Y"
Now showing items 1-1 of 1
-
Average Reward Actor-Critic with Deterministic Policy Search
The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average ...