Being curious about the answers to questions: novelty search with learned attention
arXiv:1806.00201
Abstract
We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies. The space is structured towards answering a particular distribution of questions, which are used in a supervised way to train the attentional neural network. We find that in a 2d exploration task, the structure of the space successfully encodes local sensory-motor contingencies such that even a greedy local `do the most novel action' policy with no reinforcement learning or evolution can explore the space quickly. We also apply this to a high/low number guessing game task, and find that guessing according to the learned attention profile performs active inference and can discover the correct number more quickly than an exact but passive approach.
arXiv comment8 pages, 7 figures, ALife 2018
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
- VIME: Variational Information Maximizing Exploration
- Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
- Count-Based Exploration with Neural Density Models
- Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
- Diversity is All You Need: Learning Skills without a Reward Function
- Curiosity-driven reinforcement learning with homeostatic regulation
- Learning body-affordances to simplify action spaces