2 papers
cs.LG2025
Reducing Reward Dependence in RL Through Adaptive Confidence Discounting
Muhammed Yusuf Satici, David L. Roberts
In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cos…
cs.LG2025
Autonomous Curriculum Design via Relative Entropy Based Task Modifications
Muhammed Yusuf Satici, Jianxun Wang, David L. Roberts
Curriculum learning is a training method in which an agent is first trained on a curriculum of relatively simple tasks related to a target task in an effort to shorten the time req…