4 papers
Policy as Data: Replay-Based Policy Dual Averaging via Advantage Regression
Nianli Peng, Geoffrey J. Gordon, Kianté Brantley
Actor-critic methods reuse past experience to improve sample efficiency. However, historical data are typically regarded as off-policy samples for the current policy-improvement up…
Efficient and Scalable Deep Reinforcement Learning for Mean Field Control Games
Nianli Peng, Yilin Wang
Mean Field Control Games (MFCGs) provide a powerful theoretical framework for analyzing systems of infinitely many interacting agents, blending elements from Mean Field Games (MFGs…
Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
Nianli Peng, Muhang Tian, Brandon Fain
We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewar…
Welfare and Fairness in Multi-objective Reinforcement Learning
Zimeng Fan, Nianli Peng, Muhang Tian +1
We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward…