Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Explore this paper's citation graph

Summary

This article will discuss how a generalization of the reinforcement learning or optimal control problem, which is sometimes termed maximum entropy reinforcement learning, is equivalent to exact probabilistic inference in the case of deterministic dynamics, and variational inference inThe case of stochastic dynamics.

Type
preprint
Published
2018-05-02
Cited by
895
References
64
Access
Open access

Keywords

Reinforcement learning, Inference, Probabilistic logic, Reinforcement, Computer science

References

Cited by

Related papers