Miroslav Pajic

Beyond Worst-Case: Efficient Robust RL via In-Context Generalization

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

DEPART: Hierarchical Multi-Agent System for Multi-Turn Interaction

On Trajectory Augmentations for Off-Policy Evaluation

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Robust Reinforcement Learning with Structured Adversarial Ensemble

Universal Off-Policy Selection for Human-Centric Systems via Participant Sub-grouping

Off-Policy Selection for Initiating Human-Centric Experimental Design

D2T2: Decision Transformer with Temporal Difference via Steering Guidance