paper-with-me

Papers

Communicating via Markov Decision Processes

2021-07-17 · Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl, Luisa Zintgraf, Philip Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob Foerster

We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes both source coding and a large class of referential games. MCGs also isolate a problem that is important in decentralized control settings in which cheap-talk is not available -- namely, they require balancing communication with the associated cost of communicating. We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME. Due to recent breakthroughs in approximation algorithms for minimum entropy coupling, MEME is not merely a theoretical algorithm, but can be applied to practical settings. Empirically, we show both that MEME is able to outperform a strong baseline on small MCGs and that MEME is able to achieve strong performance on extremely large MCGs. To the latter point, we demonstrate that MEME is able to losslessly communicate binary images via trajectories of Cartpole and Pong, while simultaneously achieving the maximal or near maximal expected returns, and that it is even capable of performing well in the presence of actuator noise.

📄 PDF Abstract BibTeX arXiv:2107.08295

Code (1)

schroederdewitt/meme 공식 구현 pytorch

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

On Convergence of Average-Reward Q-Learning in Weakly Communicating Markov Decision Processes

2024-08-29 · Yi Wan, Huizhen Yu, Richard S. Sutton

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes (MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on relative value iteration (RVI), which are mod…

Q-LearningReinforcement Learning (RL)

Models and algorithms for skip-free Markov decision processes on trees

2013-09-17 · E. J. Collins

We introduce a class of models for multidimensional control problems which we call skip-free Markov decision processes on trees. We describe and analyse an algorithm applicable to Markov decision processes of this type t…

Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints

2022-01-31 · Liyu Chen, Rahul Jain, Haipeng Luo

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimat…

Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes

2018-07-06 · NeurIPS 2018 12 · Ronan Fruit, Matteo Pirotta, Alessandro Lazaric

While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are…

Efficient Exploration

Improved Analysis of UCRL2 with Empirical Bernstein Inequality

2020-07-10 · Ronan Fruit, Matteo Pirotta, Alessandro Lazaric

We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $\…