Goal-Conditioned Reinforcement Learning: Problems and Solutions

Minghuan Liu; Menghui Zhu; Weinan Zhang

Goal-Conditioned Reinforcement Learning: Problems and Solutions

Artificial Intelligence 2022-09-05 v3 Machine Learning

Authors: Minghuan Liu , Menghui Zhu , Weinan Zhang

Abstract

Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on the states or observations, GCRL additionally requires the agent to make decisions according to different goals. In this survey, we provide a comprehensive overview of the challenges and algorithms for GCRL. Firstly, we answer what the basic problems are studied in this field. Then, we explain how goals are represented and present how existing solutions are designed from different points of view. Finally, we make the conclusion and discuss potential future prospects that recent researches focus on.

Keywords

reinforcement learning hierarchical reinforcement learning multi-agent reinforcement learning

Cite

@article{arxiv.2201.08299,
  title  = {Goal-Conditioned Reinforcement Learning: Problems and Solutions},
  author = {Minghuan Liu and Menghui Zhu and Weinan Zhang},
  journal= {arXiv preprint arXiv:2201.08299},
  year   = {2022}
}

Comments

10 pages, 3 figures, 2 tables. Published at IJCAI-ECAI 2022 (Survey Track). Add clarified words

Goal-Conditioned Reinforcement Learning: Problems and Solutions

Abstract

Keywords

Cite

Comments

Related papers