The authors studied the Bayesian regret of unmodified posterior sampling for reinforcement learning (PSRL) in finite-horizon, time-inhomogeneous Markov decision processes.
Unmodified posterior sampling achieves minimax regret in reinforcement learning
For tabular and linear-mixture MDPs, vanilla PSRL attains the minimax regret rate without structural assumptions on the prior.
Top University
Taewon Goo · Kihyuk Hong
KAIST
Research Digest··3 min read
Goo and Hong prove that exact vanilla posterior sampling for reinforcement learning (PSRL) is minimax optimal in leading-order Bayesian regret for finite-horizon time-inhomogeneous tabular MDPs with unknown stochastic rewards, achieving the rate Õ(√(SAH³K)).
Why this paper
From KAIST
In one line
Posterior sampling for reinforcement learning is minimax optimal without structural prior assumptions.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§