Meta-learning within Projective Simulation

02/25/2016
by   Adi Makmal, et al.
0

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal, approach. Most non-trivial models thus require the adjustment of several to many learning parameters, which is often done on a case-by-case basis by an external party. Meta-learning refers to the ability of an agent to autonomously and dynamically adjust its own learning parameters, or meta-parameters. In this work we show how projective simulation, a recently developed model of artificial intelligence, can naturally be extended to account for meta-learning in reinforcement learning settings. The projective simulation approach is based on a random walk process over a network of clips. The suggested meta-learning scheme builds upon the same design and employs clip networks to monitor the agent's performance and to adjust its meta-parameters "on the fly". We distinguish between "reflexive adaptation" and "adaptation through learning", and show the utility of both approaches. In addition, a trade-off between flexibility and learning-time is addressed. The extended model is examined on three different kinds of reinforcement learning tasks, in which the agent has different optimal values of the meta-parameters, and is shown to perform well, reaching near-optimal to optimal success rates in all of them, without ever needing to manually adjust any meta-parameter.

READ FULL TEXT

page 8

page 11

research
11/26/2020

Meta-learning in natural and artificial intelligence

Meta-learning, or learning to learn, has gained renewed interest in rece...
research
04/24/2023

Awesome-META+: Meta-Learning Research and Learning Platform

Artificial intelligence technology has already had a profound impact in ...
research
10/30/2019

Decoupling Adaptation from Modeling with Meta-Optimizers for Meta Learning

Meta-learning methods, most notably Model-Agnostic Meta-Learning or MAML...
research
01/01/2021

B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning

There is a growing interest in the learning-to-learn paradigm, also know...
research
04/05/2019

Synthesized Policies for Transfer and Adaptation across Tasks and Environments

The ability to transfer in reinforcement learning is key towards buildin...
research
10/04/2021

Behaviour-conditioned policies for cooperative reinforcement learning tasks

The cooperation among AI systems, and between AI systems and humans is b...
research
08/22/2022

Quantum Multi-Agent Meta Reinforcement Learning

Although quantum supremacy is yet to come, there has recently been an in...

Please sign up or login with your details

Forgot password? Click here to reset