reward functions
In reinforcement learning, a reward function defines how rewards are given to an agent based on its actions and the state of the environment, guiding the learning process towards achieving specific goals.
- Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding
- GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
- No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
- Pairwise Calibrated Rewards for Pluralistic Alignment
- Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
- RF-Agent: Automated Reward Function Design via Language Agent Tree Search
- Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
- TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
- Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
- Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
- Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
- Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts