Information theoretic MPC for model-based reinforcement learning | IEEE Conference Publication | IEEE Xplore

Information theoretic MPC for model-based reinforcement learning

Publisher: IEEE

Abstract:

We introduce an information theoretic model predictive control (MPC) algorithm capable of handling complex cost criteria and general nonlinear dynamics. The generality of...View more

Abstract:

We introduce an information theoretic model predictive control (MPC) algorithm capable of handling complex cost criteria and general nonlinear dynamics. The generality of the approach makes it possible to use multi-layer neural networks as dynamics models, which we incorporate into our MPC algorithm in order to solve model-based reinforcement learning tasks. We test the algorithm in simulation on a cart-pole swing up and quadrotor navigation task, as well as on actual hardware in an aggressive driving task. Empirical results demonstrate that the algorithm is capable of achieving a high level of performance and does so only utilizing data collected from the system.
Date of Conference: 29 May 2017 - 03 June 2017
Date Added to IEEE Xplore: 24 July 2017
ISBN Information:
Publisher: IEEE
Conference Location: Singapore

References

References is not available for this document.