Options Discovery with Budgeted Reinforcement Learning
arXiv:1611.06824
Abstract
We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demonstrating both quantitative and qualitative interesting results.
Under review as a conference paper at IJCAI 2017
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Hierarchical Multiscale Recurrent Neural Networks
- Hierarchical Solution of Markov Decision Processes using Macro-actions
- Variational Intrinsic Control
- Learning and Transfer of Modulated Locomotor Controllers
- Strategic Attentive Writer for Learning Macro-Actions