reinforcement learning

Reinforcement learning-driven adaptive stealthy attacks manipulating battery state of health estimation

Adaptive Firewall Policy Optimization Based on Multi-Objective Reinforcement Learning

Hierarchical reinforcement learning for cost-effective railway microgrid management

Adaptive impedance control of wall-building robots in nonlinear viscoelastic environments using fuzzy wavelet neural networks and reinforcement learning

Deep reinforcement learning-based energy management strategy for unmanned aerial vehicles powered by solar cells and lithium polymer battery

Data-driven scheduling of hydrogen-integrated energy systems: An offline reinforcement learning approach with constraint-aware safety projection

Incremental reinforcement learning for safe optimal control of unknown nonlinear systems

Spatiotemporal synergistic control for mixed traffic bottlenecks: Multi-agent reinforcement learning with attention and prior liveness bounds

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

DEX-Comp is proposed, a two-stage training recipe that separates reliable imitation from targeted exploration and applies outcome-based reinforcement learning to teacher-failed questions to directly optimize answer correctness.

Generating Constructive Feedback on Stories via Reinforcement Learning

Constructive feedback is crucial for creative writers to refine their storytelling abilities. Since receiving feedback from human experts is often costly and time-intensive, large language models (LLMs) offer a scalable and efficient alternative as automatic writing assistants. Despite their potential, research indicat...

Dynamic Bayesian Optimization with Reinforcement Learning

Bayesian Optimization (BO) is a powerful technique for optimizing black-box functions, particularly those where gradient information is unavailable. However, its performance can degrade significantly when faced with noisy or non-stationary objective functions. This paper proposes a novel approach, Dynamic Bayesian Opti...

Adaptive Kernel Learning via Meta-Reinforcement for Feature Selection

The selection of an appropriate kernel function remains a significant challenge in kernel methods, frequently relying on manual tuning and heuristic approaches. This research introduces a novel framework employing meta-reinforcement learning to autonomously learn and adapt kernel functions. The system utilizes a reinfo...