DeepAI
Log In Sign Up

Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models

02/22/2021
by   Jan Achterhold, et al.
0

In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments.

READ FULL TEXT
06/08/2021

LEADS: Learning Dynamical Systems that Generalize Across Environments

When modeling dynamical systems from real-world data samples, the distri...
03/22/2019

DQN with model-based exploration: efficient learning on environments with sparse rewards

We propose Deep Q-Networks (DQN) with model-based exploration, an algori...
01/27/2022

The Challenges of Exploration for Offline Reinforcement Learning

Offline Reinforcement Learning (ORL) enablesus to separately study the t...
06/21/2019

Variational Bridge Constructs for Grey Box Modelling with Gaussian Processes

This paper introduces a method for inference of heterogeneous dynamical ...
02/10/2021

Task-Optimal Exploration in Linear Dynamical Systems

Exploration in unknown environments is a fundamental problem in reinforc...
10/02/2017

Unsupervised Learning for Nonlinear PieceWise Smooth Hybrid Systems

This paper introduces a novel system identification and tracking method ...
04/25/2018

A Note on Kernel Methods for Multiscale Systems with Critical Transitions

We study the maximum mean discrepancy (MMD) in the context of critical t...