DeepAI AI Chat
Log In Sign Up

Control-Tutored Reinforcement Learning

by   Francesco De Lellis, et al.

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some limited knowledge of the plant encoded into a tutoring model-based control strategy. We illustrate the benefits of our novel approach and its effectiveness by using the problem of controlling one or more agents to herd and contain within a goal region a set of target free-roving agents in the plane.


page 1

page 2

page 3

page 4


Tutoring Reinforcement Learning via Feedback Control

We introduce a control-tutored reinforcement learning (CTRL) algorithm. ...

Successor Features Support Model-based and Model-free Reinforcement Learning

One key challenge in reinforcement learning is the ability to generalize...

Herding stochastic autonomous agents via local control rules and online global target selection strategies

In this Letter we propose a simple yet effective set of local control ru...

Bayesian Curiosity for Efficient Exploration in Reinforcement Learning

Balancing exploration and exploitation is a fundamental part of reinforc...

Control-Tutored Reinforcement Learning: an application to the Herding Problem

In this extended abstract we introduce a novel control-tutored Q-learni...

Reinforcement Learning with Subspaces using Free Energy Paradigm

In large-scale problems, standard reinforcement learning algorithms suff...

Decoupling Strategy and Generation in Negotiation Dialogues

We consider negotiation settings in which two agents use natural languag...