paper-with-me

홈 › Papers

Reward-Conditioned Reinforcement Learning

2026-03-05 · Michal Nauman, Marek Cygan, Pieter Abbeel arxiv

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning (RCRL), an off-policy method that conditions agents on reward parameterizations while collecting experience under a single nominal objective. By recomputing counterfactual rewards from shared replay data, RCRL exposes the agent to multiple reward objectives without additional environment interaction, connecting single-task RL with ideas from multi-objective and multi-task learning. Across single-task, multi-task, and vision-based benchmarks, RCRL improves sample efficiency under the nominal reward parameterization, enables efficient adaptation to new parameterizations, and supports zero-shot behavioral adjustment at deployment. Our results show that RCRL provides a scalable mechanism for learning robust, steerable policies without sacrificing the simplicity of single-task training.

📄 PDF Abstract BibTeX arXiv:2603.05066

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMulti-Task Learning

Similar Papers 제목 키워드 기반

Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control

2025-12-06 · Nathan P. Lawrence, Ali Mesbah arxiv

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on …

Reinforcement Learning

From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following

2019-02-20 · ICLR 2019 5 · Justin Fu, Anoop Korattikara, Sergey Levine, Sergio Guadarrama

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks …

Instruction Followingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning

2022-06-24 · Yunfei Li, Tian Gao, Jiaqi Yang, Huazhe Xu 외

It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tack…

reinforcement-learningReinforcement Learning (RL)

Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization

2023-12-10 · Takuya Hiraoka

Reinforcement learning (RL) methods with a high replay ratio (RR) and regularization have gained interest due to their superior sample efficiency. However, these methods have mainly been developed for dense-reward tasks.…

Q-LearningReinforcement Learning (RL)

Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning

2021-04-11 · Jinxin Liu, Donglin Wang, Qiangxing Tian, Zhengyu Chen

It is of significance for an agent to learn a widely applicable and general-purpose policy that can achieve diverse goals including images and text descriptions. Considering such perceptually-specific goals, the frontier…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)