5 papers
Robust Nash Alignment under Preference Uncertainty
Shihab Ahmed, Debamita Ghosh, David Tang +3
Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are uncertain: noisy, heterogeneous,…
Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation
Debamita Ghosh, George K. Atia, Yue Wang
Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic interactions among agents. Di…
Online Robust Reinforcement Learning with General Function Approximation
Debamita Ghosh, George K. Atia, Yue Wang
In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training…
ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning
Debamita Ghosh, George K. Atia, Yue Wang
We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in pr…
Sample-Efficient Distributionally Robust Multi-Agent Reinforcement Learning via Online Interaction
Zain Ulabedeen Farhat, Debamita Ghosh, George K. Atia +1
Well-trained multi-agent systems can fail when deployed in real-world environments due to model mismatches between the training and deployment environments, caused by environment u…