Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning
From MaRDI portal
information theoryMarkov gamesrate-distortion theoryposterior samplingmulti-agent reinforcement learningsample-efficient algorithms
Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) General considerations in statistical decision theory (62C05) Markov and semi-Markov decision processes (90C40) Stochastic games, stochastic differential games (91A15) Rate-distortion theory in information and communication theory (94A34)
Cites work
- A Tutorial on Thompson Sampling
- Almost optimal algorithms for two-player zero-sum linear mixture Markov games
- An algorithm for computing the capacity of arbitrary discrete memoryless channels
- Bayesian model averaging: A tutorial. (with comments and a rejoinder).
- Computation of channel capacity and rate-distortion functions
- Learning to optimize via information-directed sampling
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Pessimistic value iteration for multi-task data sharing in offline reinforcement learning
- Provably efficient reinforcement learning in decentralized general-sum Markov games
- Reinforcement Learning, Bit by Bit
- V-learning -- a simple, efficient, decentralized algorithm for multiagent reinforcement learning
This page was built for publication: Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6916841)
