The paper proposes a Hierarchical Reinforcement Learning framework with two levels for handling high-level strategic planning and low-level continuous-control using Soft Actor-Critic and entropy-regul…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

The paper proposes S3TS, a novel tree search algorithm that simultaneously handles both non-linear system models and explicit uncertainties (scenarios) for advanced energy planning, achieving near-opt…

This paper demonstrates that a complex deep reinforcement learning policy for power grid control can be successfully distilled into a lightweight, auditable decision tree and random forest surrogate t…

The paper introduces Nested Contextual Causal Bandits (NCCBs) to model multi-timescale sequential decisions and proposes a certified policy optimization method, NCTS, that provides quantifiable risk b…

The paper proposes Hysteretic Policy Optimization (HPO) and its adaptive variant (A-HPO) to stabilize reinforcement learning training in sparse-reward environments by better balancing positive and neg…

This paper shows that standard optimal control in Markov Decision Processes (MDPs) with an absorbing catastrophic state naturally generates behavioral signatures mimicking prospect theory, even withou…

This paper analyzes the effect of using stale rollouts in asynchronous GRPO and derives a stability condition.

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

This paper proposes an approximation algorithm for the submodular joint replenishment problem with decomposable submodular ordering cost functions, achieving an O(k)-approximation.

The paper introduces a queueing-theoretic framework to model dynamic cyber-attack surfaces, developing an adaptive reinforcement learning defense policy that significantly reduces active vulnerabiliti…

The paper proposes ReCAP, a novel continual learning framework for portfolio management, which adaptively combines policies from a library based on detected market regimes to achieve superior long-ter…

This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.

The paper introduces a learned 'rerooter' mechanism to improve subgoal-based policy tree search, allowing scalable search in complex environments without the overhead of explicit subgoal generation.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating t…

The paper proposes a novel Bayesian framework to learn the optimal decision strategy for the stochastic shortest path problem by directly constructing the posterior beliefs for the action-value functi…

The paper develops and validates a novel Deep Reinforcement Learning (DRL) framework to enhance pair trading in volatile cryptocurrency markets, demonstrating statistically significant outperformance…