Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed ...

Abstract: Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in ...

This paper proposes an exploration-efficient deep reinforcement learning with reference (DRLR) policy framework for learning robotics tasks incorporating demonstrations. The DRLR framework is ...

An overview of our research on agentic RL. In this work, we systematically investigate three dimensions of agentic RL: data, algorithms, and reasoning modes. Our findings reveal: Real end-to-end ...

The path planning capability of autonomous robots in complex environments is crucial for their widespread application in the real world. However, long-term decision-making and sparse reward signals ...

Abstract: Safe reinforcement learning (Safe RL) aims to learn policies capable of learning and adapting within complex environments while ensuring actions remain free from catastrophic consequences.