AI Chat AI Image Generator AI Video Text to Speech

Goal-Conditioned Reinforcement Learning: Problems and Solutions

01/20/2022

∙

by Minghuan Liu, et al.

∙

∙

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.

Minghuan Liu
13 publications
Menghui Zhu
5 publications
Weinan Zhang
146 publications

page 1

page 2

page 3

page 4

research

∙ 04/27/2022

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Building generalizable goal-conditioned agents from rich observations is...

0 Philippe Hansen-Estruch, et al. ∙

research

∙ 12/17/2020

Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

Building autonomous machines that can explore open-ended environments, d...

32 Cédric Colas, et al. ∙

research

∙ 07/17/2018

Reinforcement Learning for LTLf/LDLf Goals

MDPs extended with LTLf/LDLf non-Markovian rewards have recently attract...

0 Giuseppe De Giacomo, et al. ∙

research

∙ 11/17/2020

C-Learning: Learning to Achieve Goals via Recursive Classification

We study the problem of predicting and controlling the future state dist...

12 Benjamin Eysenbach, et al. ∙

research

∙ 06/22/2018

Many-Goals Reinforcement Learning

All-goals updating exploits the off-policy nature of Q-learning to updat...

0 Vivek Veeriah, et al. ∙

research

∙ 03/26/2023

Learning Generative Models with Goal-conditioned Reinforcement Learning

We present a novel, alternative framework for learning generative models...

0 Mariana Vargas Vieyra, et al. ∙

research

∙ 11/13/2022

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary

Reinforcement learning has seen increasing applications in real-world co...

0 Carlos Purves, et al. ∙