How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy

12/14/2021
by   Badr AlKhamissi, et al.
0

Alchemy is a new meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make fine-grained analysis tractable. Further, Alchemy provides an optional symbolic interface that enables meta-RL research without a large compute budget. In this work, we take the first steps toward using Symbolic Alchemy to identify design choices that enable deep-RL agents to learn various types of abstraction. Then, using a variety of behavioral and introspective analyses we investigate how our trained agents use and represent abstract task variables, and find intriguing connections to the neuroscience of abstraction. We conclude by discussing the next steps for using meta-RL and Alchemy to better understand the representation of abstract variables in the brain.

READ FULL TEXT

page 5

page 10

research
04/04/2022

Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning

The ability to acquire abstract knowledge is a hallmark of human intelli...
research
11/07/2022

Symbolic Abstract Heaps for Polymorphic Information-flow Guard Inference (Extended Version)

In the realm of sound object-oriented program analyses for information-f...
research
02/04/2021

Alchemy: A structured task distribution for meta-reinforcement learning

There has been rapidly growing interest in meta-learning as a method for...
research
08/24/2022

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Meta-learning is a line of research that develops the ability to leverag...
research
12/19/2018

Modular meta-learning in abstract graph networks for combinatorial generalization

Modular meta-learning is a new framework that generalizes to unseen data...
research
04/07/2021

The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL

In this work, we analyze the reinstatement mechanism introduced by Ritte...
research
11/20/2022

Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines

Natural and formal languages provide an effective mechanism for humans t...

Please sign up or login with your details

Forgot password? Click here to reset