Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

by   Tongzhou Mu, et al.
University of California, San Diego

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit from expert knowledge rather than having to discover the best action to take through exploration. In this survey, we discuss the advantages of using demonstrations in sequential decision making, various ways to apply demonstrations in learning-based decision making paradigms (for example, reinforcement learning and planning in the learned models), and how to collect the demonstrations in various scenarios. Additionally, we exemplify a practical pipeline for generating and utilizing demonstrations in the recently proposed ManiSkill robot learning benchmark.


page 8

page 9

page 10


Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications

Inverse reinforcement learning (IRL) infers a reward function from demon...

Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations

Combined with demonstrations, deep reinforcement learning can efficientl...

Safe Decision-making for Lane-change of Autonomous Vehicles via Human Demonstration-aided Reinforcement Learning

Decision-making is critical for lane change in autonomous driving. Reinf...

"Guess what I'm doing": Extending legibility to sequential decision tasks

In this paper we investigate the notion of legibility in sequential deci...

Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning

To collaborate well with robots, we must be able to understand their dec...

Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks

A longstanding goal of artificial intelligence is to create artificial a...

Please sign up or login with your details

Forgot password? Click here to reset