DeepAI AI Chat
Log In Sign Up

A Bayesian Approach to Policy Recognition and State Representation Learning

05/04/2016
by   Adrian Šošić, et al.
Technische Universität Darmstadt
0

Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert. These models can be used e.g. for system control by generalizing the expert demonstrations to previously unencountered situations. Most LfD methods, however, make strong assumptions about the expert behavior, e.g. they assume the existence of a deterministic optimal ground truth policy or require direct monitoring of the expert's controls, which limits their practical use as part of a general system identification framework. In this work, we consider the LfD problem in a more general setting where we allow for arbitrary stochastic expert policies, without reasoning about the optimality of the demonstrations. Following a Bayesian methodology, we model the full posterior distribution of possible expert controllers that explain the provided demonstration data. Moreover, we show that our methodology can be applied in a nonparametric context to infer the complexity of the state representation used by the expert, and to learn task-appropriate partitionings of the system state space.

READ FULL TEXT
01/04/2021

Robust Maximum Entropy Behavior Cloning

Imitation learning (IL) algorithms use expert demonstrations to learn a ...
03/23/2021

Ground Truths for the Humanities

Ensuring a faithful interaction with data and its representation for hum...
06/17/2021

Learning from Demonstration without Demonstrations

State-of-the-art reinforcement learning (RL) algorithms suffer from high...
09/13/2020

Toward the Fundamental Limits of Imitation Learning

Imitation learning (IL) aims to mimic the behavior of an expert policy i...
03/09/2022

Learning to control from expert demonstrations

In this paper, we revisit the problem of learning a stabilizing controll...
12/20/2021

Demonstration Informed Specification Search

This paper considers the problem of learning history dependent task spec...