Timezone: »

 
Poster
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
Yuda Song · Wen Sun

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 1 »

Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a computationally and statistically efficient model-based algorithm for both Kernelized Nonlinear Regulators (KNR) and linear Markov Decision Processes (MDPs). For both models, our algorithm guarantees polynomial sample complexity and only uses access to a planning oracle. Experimentally, we first demonstrate the flexibility and the efficacy of our algorithm on a set of exploration challenging control tasks where existing empirical model-based RL approaches completely fail. We then show that our approach retains excellent performance even in common dense reward control benchmarks that do not require heavy exploration.

Keywords: Reinforcement Learning and Planning

Author Information

Yuda Song (Carnegie Mellon University)
Wen Sun (Cornell University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors