Adapting Behaviour for Learning Progress
Preprint
Abstract
Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has not removed the need to tune exploration to the task, because the ideal data for the learning algorithm necessarily depends on its process of learning. We propose to dynamically adapt the data generation by using a non-stationary multi-armed bandit to optimize a proxy of the learning progress. The data distribution is controlled by modulating multiple parameters of the policy (such as stochasticity, consistency or optimism) without significant overhead. The adaptation speed of the bandit can be increased by exploiting the factored modulation structure. We demonstrate on a suite of Atari 2600 games how this unified approach produces results comparable to per-task tuning at a fraction of the cost.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Adapting Behavior via Intrinsic Reward: A Survey and Empirical StudyJournal of Artificial Intelligence Research, 2020
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents2019
- Intrinsic Motivation Systems for Autonomous Mental DevelopmentIEEE Transactions on Evolutionary Computation, 2007
- A Class of Distortion Operators for Pricing Financial and Insurance RisksJournal of Risk and Insurance, 2000