2012
NeurIPS
NeurIPS 2012
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
Abstract
We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds for implementing optimism in the face of uncertainty. Beside the existence of an optimal policy which satisfies the Poisson equation, the only assumptions made are Hoelder continuity of rewards and transition probabilities.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Reinforcement Learning
🐣
Hot Topic Early Bird
- upper confidence bound
Authors
Topics
Machine Learning > Optimization & Theory > Learning Theory
Reinforcement Learning > Methods
Reinforcement Learning > Methods > Deep RL
Reinforcement Learning > Methods > Policy Learning
Machine Learning > Learning Types > Online Learning
Machine Learning > Learning Types > Reinforcement Learning
Machine Learning > Optimization & Theory > Online Algorithms