2012
NeurIPS
NeurIPS 2012
Cost-Sensitive Exploration in Bayesian Reinforcement Learning
Abstract
In this paper, we consider Bayesian reinforcement learning (BRL) where actions incur costs in addition to rewards, and thus exploration has to be constrained in terms of the expected total cost while learning to maximize the expected long-term total reward. In order to formalize cost-sensitive exploration, we use the constrained Markov decision process (CMDP) as the model of the environment, in which we can naturally encode exploration requirements using the cost function. We extend BEETLE, a model-based BRL method, for learning in the environment with cost constraints. We demonstrate the cost-sensitive exploration behaviour in a number of simulated problems.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Reinforcement Learning
📈
Trend Setter
- Markov Decision Process
🐣
Hot Topic Early Bird
- model-based reinforcement learning
Authors
Topics
Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning
Machine Learning > Optimization & Theory > Bayesian Inference
Reinforcement Learning > Methods > Deep RL
Reinforcement Learning > Methods > Offline RL
Machine Learning > Bayesian & Probabilistic > Bayesian Learning
Machine Learning > Learning Types > Reinforcement Learning
Artificial Intelligence > Core AI > Reinforcement Learning
Machine Learning > Learning Types > Exploration-Exploitation
Reinforcement Learning > Methods > Model-Based RL
Machine Learning > Learning Types > Markov Decision Process