reinforcement learning

A comprehensive survey on connectivity for IoT sensor networks

This paper presents various feature scopes used in wireless sensor networks (WSNs) and illustrates distinct approaches like relay node placement, efficient communication, machine-learning systems i.e. reinforcement learning, and heuristic techniques.

CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses

Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in untrusted tool outputs and can covertly alter the execution of a legitimate task. Defenses trained on fixed attacks may fail as an attacker changes its strategy, inject...

Temporal-Causal Inference for Reinforcement Learning via Automata Learning

Temporal-Causal Inference for Reinforcement Learning (TCIRL), a framework that jointly learns a control policy and infers the hidden temporal cause of the phase transition and recovers the correct cause DFA and matches the full-information baseline in both domains.

One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control

OSOL, which designates a focus domain at each iteration, uses the preceding checkpoint footprint to rank token-level rebound risk, and applies a drift-ranked, adaptively scaled correction within the standard GRPO update, is proposed, which suppresses the targeted cross-step output backtracking component.

Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning

A noisy-space action-value (Q-)function that assigns values to diffusion latents through the distribution of executed actions induced by the denoising process is introduced, which admits a precise semantic interpretation and derives a noisy-space policy gradient (NSPG) that optimizes noisy latents using only clean acti...

Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference

These results establish a Grover-based realization of path-integral slow thinking: the interior target preserves exploratory path diversity, and ensemble-level interference converts it into verified performance.

VD-E2E: A hybrid reinforcement learning approach integrating vehicle-drone perception for end-to-end automated parking

Path-power joint allocation based on improved hierarchical reinforcement learning method for distributed cooperative jamming

Heterogeneous deformation behavior and workability of Mg/Al bimetals during thermomechanical processing: A reinforcement learning-based process regulation method

DHRL-JARSS: SDN-based Deep Hierarchical Reinforcement Learning for QoS-aware Joint Access-Routing Scheduling in multi-link intelligent ship network

Autonomous global-minimum search of Pd6Mo7 nanoclusters from deep reinforcement learning

Autonomous sailing with sim-to-real reinforcement learning