Tag
This paper proposes Action-Conditioned Risk Gating, a lightweight reinforcement learning method for risk-sensitive control under partial observability that uses a compact finite-history proxy state and an action-conditioned near-term risk predictor to balance safety and performance.
This paper proposes reusable certified runtime monitors for past-time signal temporal logic (ptSTL) that use semantic latent representations to evaluate varying specifications without retraining, validated on pedestrian-crossroad and Waymo driving data.
IntentVLA is a history-conditioned visual-language-action framework that improves robot imitation learning stability by encoding short-horizon intents from visual observations, addressing challenges from partial observability and ambiguous observations. It also introduces AliasBench, an ambiguity-aware benchmark for evaluating such methods.
This paper introduces Agent-BRACE, a method that decouples LLM agents into belief state and policy models to handle long-horizon tasks in partially observable environments. By verbalizing state uncertainty, it achieves significant performance improvements over baselines while maintaining constant context window size.
This paper introduces Pinductor, a method that uses language model priors to efficiently learn POMDP world models from limited observation-action data, achieving performance comparable to methods with privileged hidden state access while surpassing traditional tabular approaches.
This paper introduces BeliefMem, a novel memory paradigm for LLM agents that stores multiple candidate conclusions with probabilities to handle partial observability and reduce self-reinforcing errors. Empirical evaluations show it outperforms deterministic baselines on LoCoMo and ALFWorld benchmarks.
This paper introduces Neural Co-state Policies, establishing a formal link between recurrent reinforcement learning hidden states and the Pontryagin minimum principle to improve interpretability and robustness.