An infra-Bayesian RL agent is implemented that achieves lower worst-case regret than classical RL agents in environments with Knightian uncertainty and selects the optimal action in Newcomb's problem.
Title resolution pending
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
An infra-Bayesian RL agent is implemented that achieves lower worst-case regret than classical RL agents in environments with Knightian uncertainty and selects the optimal action in Newcomb's problem.