One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning
arXiv:2111.00206
Abstract
Self-tuning algorithms that adapt the learning process online encourage more effective and robust learning. Among all the methods available, meta-gradients have emerged as a promising approach. They leverage the differentiability of the learning rule with respect to some hyper-parameters to adapt them in an online fashion. Although meta-gradients can be accumulated over multiple learning steps to avoid myopic updates, this is rarely used in practice. In this work, we demonstrate that whilst multi-step meta-gradients do provide a better learning signal in expectation, this comes at the cost of a significant increase in variance, hindering performance. In the light of this analysis, we introduce a novel method mixing multiple inner steps that enjoys a more accurate and robust meta-gradient signal, essentially trading off bias and variance in meta-gradient estimation. When applied to the Snake game, the mixing meta-gradient algorithm can cut the variance by a factor of 3 while achieving similar or higher performance.
arXiv comment14 pages, 6 figures, 2 tables
References in corpus (8)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Meta-Reinforcement Learning of Structured Exploration Strategies
- Discovering Reinforcement Learning Algorithms
- Improving Generalization in Meta Reinforcement Learning using Learned Objectives
- Understanding and correcting pathologies in the training of learned optimizers
- Meta-Gradient Reinforcement Learning with an Objective Discovered Online
- A Self-Tuning Actor-Critic Algorithm
- Beyond Exponentially Discounted Sum: Automatic Learning of Return Function