Information theoretic MPC for model-based reinforcement learning
| Autor: | Nolan Wagener, James M. Rehg, Byron Boots, Brian Goldfain, Paul Drews, Grady Williams, Evangelos A. Theodorou |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Artificial neural network Computer science business.industry 020208 electrical & electronic engineering 02 engineering and technology Optimal control Machine learning computer.software_genre Task (project management) Nonlinear system Model predictive control 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering Trajectory Robot Reinforcement learning Artificial intelligence business computer |
| Zdroj: | ICRA |
| DOI: | 10.1109/icra.2017.7989202 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|