Intervention on a fixed-size recurrent state enables contextual control in sequential decisions without memory growth or direct context input.
Littman, and Anthony R
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines.
Sequential quantum state discrimination is cast as a POMDP with regular-grid discretization, subsuming one-shot minimum-error discrimination, with error bounds, complexity analysis, and examples for binary and trine states.
citing papers explorer
-
Contextual Control without Memory Growth in a Context-Switching Task
Intervention on a fixed-size recurrent state enables contextual control in sequential decisions without memory growth or direct context input.
-
Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines.
-
Projected Dynamic Programming for Sequential Quantum State Discrimination
Sequential quantum state discrimination is cast as a POMDP with regular-grid discretization, subsuming one-shot minimum-error discrimination, with error bounds, complexity analysis, and examples for binary and trine states.