Timezone: »

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

Tue Jul 20 05:35 AM -- 05:40 AM (PDT) @ None

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.

Author Information

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

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

More from the Same Authors