Emma Brunskill

Repairing Reward Functions with Human Feedback to Mitigate Reward Hacking

Behavior-Aware Off-Policy Selection in High-Stake Human-Centric Environments

SYNAPSE: Simulation Benchmark of Neuro-Adaptive Patient-Specific Evaluation for Episodic Decision-Making

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

Discovering High-Quality Chess Puzzles Through One Billion Plays with Offline Reinforcement Learning