9 citations · 11 across the 9 of their papers we have counts for
10 papers
Optimally Installing Strict Equilibria
Jeremy McMahan, Young Wu, Yudong Chen +2
In this work, we develop a reward design framework for installing a desired behavior as a strict equilibrium across standard solution concepts: dominant strategy equilibrium, Nash…
Polynomial-Time Approximability of Constrained Reinforcement Learning
Jeremy McMahan
We study the computational complexity of approximating general constrained Markov decision processes. Our primary contribution is the design of a polynomial time -additive b…
Anytime-Constrained Equilibria in Polynomial Time
Jeremy McMahan
We extend anytime constraints to the Markov game setting and the corresponding solution concept of an anytime-constrained equilibrium (ACE). Then, we present a comprehensive theory…
Inception: Efficiently Computable Misinformation Attacks on Markov Games
Jeremy McMahan, Young Wu, Yudong Chen +2
We study security threats to Markov games due to information asymmetry and misinformation. We consider an attacker player who can spread misinformation about its reward function to…
Roping in Uncertainty: Robustness and Regularization in Markov Games
Jeremy McMahan, Giovanni Artiglio, Qiaomin Xie
We study robust Markov games (RMG) with -rectangular uncertainty. We show a general equivalence between computing a robust Nash equilibrium (RNE) of a -rectangular RMG and co…
Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
Jeremy McMahan
We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key id…
Optimal Attack and Defense for Reinforcement Learning
Jeremy McMahan, Young Wu, Xiaojin Zhu +1
To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external at…
Anytime-Constrained Reinforcement Learning
Jeremy McMahan, Xiaojin Zhu
We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in…
Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
Young Wu, Jeremy McMahan, Yiding Chen +3
We study the game modification problem, where a benevolent game designer or a malevolent adversary modifies the reward function of a zero-sum Markov game so that a target determini…
Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning
Young Wu, Jeremy McMahan, Xiaojin Zhu +1
In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset. We study reward-poisoning attacks in this setting where an exogenous attacker m…