CORL: A Continuous-state Offset-dynamics Reinforcement Learner

2012/06/13 by Brunskill, Emma, Leffler, Bethany, Li, Lihong +2
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1206.3231

Abstract

Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in our bounds. Finally, we report an experiment using a robotic car driving over varying terrain to demonstrate that these dynamics representations adequately capture real-world dynamics and that our algorithm can be used to efficiently solve such problems.

Related

• Explicit Explore-Exploit Algorithms in Continuous State Spaces
• Provably Sample-Efficient RL with Side Information about Latent Dynamics
• Region Growing Curriculum Generation for Reinforcement Learning
• Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces
• Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer