AILGJan 20, 2022

Goal-Conditioned Reinforcement Learning: Problems and Solutions

arXiv:2201.08299v3217 citations
AI Analysis

This is an incremental survey paper that organizes and synthesizes existing research on GCRL for researchers in reinforcement learning.

This survey paper provides a comprehensive overview of goal-conditioned reinforcement learning (GCRL), which trains agents to achieve different goals in complex RL scenarios, explaining the basic problems, goal representations, and existing algorithmic solutions.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes