Meta-learning of Sequential Strategies

05/08/2019
by   Pedro A. Ortega, et al.
16

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains. To do so, we present basic algorithmic templates for building near-optimal predictors and reinforcement learners which behave as if they had a probabilistic model that allowed them to efficiently exploit task structure. Furthermore, we recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics. Essentially, memory-based meta-learning translates the hard problem of probabilistic sequential inference into a regression problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2020

Meta-trained agents implement Bayes-optimal agents

Memory-based meta-learning is a powerful technique to build agents that ...
research
09/21/2020

Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics

Rovers require knowledge of terrain to plan trajectories that maximize s...
research
02/06/2023

Memory-Based Meta-Learning on Non-Stationary Distributions

Memory-based meta-learning is a technique for approximating Bayes-optima...
research
05/03/2019

Meta-learners' learning dynamics are unlike learners'

Meta-learning is a tool that allows us to build sample-efficient learnin...
research
10/09/2020

Learning not to learn: Nature versus nurture in silico

Animals are equipped with a rich innate repertoire of sensory, behaviora...
research
01/11/2021

Deep Interactive Bayesian Reinforcement Learning via Meta-Learning

Agents that interact with other agents often do not know a priori what t...
research
04/12/2023

Meta-Learned Models of Cognition

Meta-learning is a framework for learning learning algorithms through re...

Please sign up or login with your details

Forgot password? Click here to reset