reinforcement learning

Adaptive Parallel-World Self-Rewarding and Cross-Model Mutual Rewarding for Large Language Models

Reward generation is a central component of reinforcement learning, preference optimization, and self-improvement in large language models (LLMs). Existing approaches have demonstrated that an LLM can evaluate its own outputs and use the resulting judgments to improve its behavior. However, self-rewarding systems may s...

Adaptive Switching Between Self-Reinforcement and Mutual Reinforcement Learning for Multiple Large Language Models

Large language models (LLMs) can generate candidate answers, evaluate their quality, and use evaluation signals to improve subsequent responses. However, self-evaluation may reinforce a model's own biases and errors, whereas evaluation by other models may introduce evaluator disagreement, capability mismatches, and cor...

Deep-Economic Dispatch: A Deep Reinforcement Learning Framework for Optimal Power Generation Scheduling in Real-Time Electricity Markets

The increasing complexity of real-time electricity markets and fluctuating load demands challenges traditional economic dispatch methods, which often fail to balance cost efficiency and system reliability. This study presents a Deep Reinforcement Learning (DRL) framework for real-time power dispatch, enabling adaptive...

Online Competitive Algorithms and Reinforcement Learning for Traffic Management

rohanwilkho/irl-reservoir-operations: Characterizing decision-making in managed hydrologic systems using Inverse Reinforcement Learning

This release contains the data and the code for Inverse Reinforcement Learning (IRL) algorithms developed to characterize reservoir operations

Virtual-Voltage-Based Multi-Agent Reinforcement Learning for Cross-Regulation Suppression in Switched-Capacitor Single-Input-Multi-Output Converters

AURA: Autonomous Urban Reconnaissance Array for Post-Earthquake Emergency Communication Networks

This paper presents AURA (Autonomous Urban Reconnaissance Array), a ROS 2-based drone swarm system designed to restore emergency WiFi communication in post-earthquake disaster zones. The system deploys five coordinated UAVs that autonomously establish a selfhealing mesh network. The architecture integrates PX4SITL with...

When Optimization Forgets the Minority: Bias Amplification in Policy-Gradient Reinforcement Learning

Bias amplification, the tendency of trained models to be more biased than the data that produced them, is well documented in supervised learning. We study it in policy-gradient reinforcement learning, where there is no static dataset: each episode belongs to a latent group that shapes the reward but is invisible to the...

Learning to Generalize Across Conditions: A PPO-Based Learning Approach to Multi-Condition Multi-Objective Optimization

This study introduces sPPO-CR, a policy-gradient deep reinforcement learning (DRL) algorithm for multi-objective (MO) and multi-condition multi-objective (MCMO) optimization. The method builds on a simplified single-step variant of Proximal Policy Optimization (PPO) and incorporates a Chebyshev-based reproduction mecha...

Deep Reinforcement Learning-Based Arbitrary Beam Pattern Synthesis for Millimeter-Wave Reconfigurable Intelligent Surfaces With Discrete Phase Shifts

Abstract Millimeter-wave reconfigurable intelligent surface (RIS) panels restricted to 1bit or 2-bit discrete phase shifts must synthesize arbitrary beam patterns from a solution space that grows exponentially with the number of reflecting elements. Existing two-dimensional finite-impulse-response filter analogies comp...

Robust high-fidelity three-qubit gates design for superconducting quantum computers via model-free reinforcement learning

Abstract Multi-qubit gates are crucial to realizing quantum algorithms. Direct implementation of these gates will facilitate a reduction in circuit depth. However, existing model-based methods rely on precise characterization of the system Hamiltonian as well as execution of the control fields, which present challenges...

Adaptive Switching between Parallel-World Self-Reinforcement and Mutual Reinforcement for Multiple Large Language Models

Large language models (LLMs) can be improved through self-generated feedback, reward-guided optimization, self-play, and interactions among multiple agents. However, a system that consistently relies on one reinforcement mode may fail to exploit complementary learning opportunities. Self-reinforcement enables an indivi...