S-Space College of Engineering/Engineering Practice School (공과대학/대학원) Dept. of Computer Science and Engineering (컴퓨터공학부) Journal Papers (저널논문_컴퓨터공학부)
EMI: Exploration with mutual information
- Issue Date
- 36th International Conference on Machine Learning, ICML 2019, Vol.2019-June, pp.5837-5851
- Copyright © 2019 ASMEReinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or discriminative modeling of novelty. We propose EMI, which is an exploration method that constructs embedding representation of states and actions that does not rely on generative decoding of the full observation but extracts predictive signals that can be used to guide exploration based on forward prediction in the representation space. Our experiments show competitive results on challenging locomotion tasks with continuous control and on image-based exploration tasks with discrete actions on Atari. The source code is available at https://github.com/snu-mllab/EMI.
- Files in This Item: There are no files associated with this item.