Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration
This work addresses efficient learning for robotic systems, offering incremental improvements in model-based reinforcement learning for specific domains.
The paper tackles robotic control by combining model identification with model predictive control, using a feature-based dynamics model and optimistic exploration to learn tasks faster than previous methods, achieving substantial speed improvements on benchmark problems like pendulum and cartpole.
In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control. We use a feature-based representation of the dynamics that allows the dynamics model to be fitted with a simple least squares procedure, and the features are identified from a high-level specification of the robot's morphology, consisting of the number and connectivity structure of its links. Model predictive control is then used to choose the actions under an optimistic model of the dynamics, which produces an efficient and goal-directed exploration strategy. We present real time experimental results on standard benchmark problems involving the pendulum, cartpole, and double pendulum systems. Experiments indicate that our method is able to learn a range of benchmark tasks substantially faster than the previous best methods. To evaluate our approach on a realistic robotic control task, we also demonstrate real time control of a simulated 7 degree of freedom arm.