ROBOTICS

REINFORCEMENT LEARNING

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning

December 15, 2021

Abstract

Accurately predicting the dynamics of robotic systems is crucial for model-based control and reinforcement learning. The most common way to estimate dynamics is by fitting a one-step ahead prediction model and using it to recursively propagate the predicted state distribution over long horizons. Unfortunately, this approach is known to compound even small prediction errors, making long-term predictions inaccurate. In this paper, we propose a new parametrization to supervised learning on state-action data to stably predict at longer horizons – that we call a trajectory-based model. This trajectory-based model takes an initial state, a future time index, and control parameters as inputs, and directly predicts the state at the future time index. Experimental results in simulated and real-world robotic tasks show that trajectory-based models yield significantly more accurate long term predictions, improved sample efficiency, and the ability to predict task reward. With these improved prediction properties, we conclude with a demonstration of methods for using the trajectory-based model for control.

Download the Paper

AUTHORS

Written by

Roberto Calandra

Nathan Owen Lambert

Albert Wilcox

Howard Zhang

Kristofer S. J. Pister

Publisher

CDC

Research Topics

Reinforcement Learning

Robotics

Related Publications

December 05, 2021

REINFORCEMENT LEARNING

Local Differential Privacy for Regret Minimization in Reinforcement Learning

Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, Matteo Pirotta

December 05, 2021

December 05, 2021

REINFORCEMENT LEARNING

Hierarchical Skills for Efficient Exploration

Jonas Gehring, Gabriel Synnaeve, andreas krause, Nicolas Usunier

December 05, 2021

November 12, 2021

THEORY

REINFORCEMENT LEARNING

Bandits with Knapsacks beyond the Worst-Case Analysis

Karthik Abinav Sankararaman, Aleksandrs Slivkins

November 12, 2021

November 09, 2021

REINFORCEMENT LEARNING

Interesting Object, Curious Agent: Learning Task-Agnostic Exploration

Simone Parisi, Victoria Dean, Deepak Pathak, Abhinav Gupta

November 09, 2021