Infra-Bayesian RL agents are shown via implementation to have lower worst-case regret than classical RL under model misspecification and to solve Newcomb's problem optimally.
Operations Research , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
Infra-Bayesian RL agents are shown via implementation to have lower worst-case regret than classical RL under model misspecification and to solve Newcomb's problem optimally.