paper-with-me

Papers

Program-Based Strategy Induction for Reinforcement Learning

2024-02-26 · Carlos G. Correa, Thomas L. Griffiths, Nathaniel D. Daw

Typical models of learning assume incremental estimation of continuously-varying decision variables like expected rewards. However, this class of models fails to capture more idiosyncratic, discrete heuristics and strategies that people and animals appear to exhibit. Despite recent advances in strategy discovery using tools like recurrent networks that generalize the classic models, the resulting strategies are often onerous to interpret, making connections to cognition difficult to establish. We use Bayesian program induction to discover strategies implemented by programs, letting the simplicity of strategies trade off against their effectiveness. Focusing on bandit tasks, we find strategies that are difficult or unexpected with classical incremental learning, like asymmetric learning from rewarded and unrewarded trials, adaptive horizon-dependent random exploration, and discrete state switching.

📄 PDF Abstract BibTeX arXiv:2402.16668

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental LearningProgram inductionreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning

2020-02-08 · NeurIPS Workshop ICBINB 2020 12 · Hannes Eriksson, Emilio Jorge, Christos Dimitrakakis, Debabrota Basu 외

Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value fun…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

2020-10-29 · EMNLP 2020 11 · Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi 외

Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the ques…

Knowledge Base Question AnsweringMeta Reinforcement LearningProgram inductionQuestion Answering+2

Neural Program Meta-Induction

2017-10-11 · NeurIPS 2017 12 · Jacob Devlin, Rudy Bunel, Rishabh Singh, Matthew Hausknecht 외

Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output mapping. This paper aims to address the …

Program inductionTransfer Learning

Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines

2022-05-23 · Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta, Raja Marjieh 외

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning ma…

Meta-LearningMeta Reinforcement LearningProgram inductionReinforcement Learning (RL)

Guided Sketch-Based Program Induction by Search Gradients

2024-02-10 · Ahmad Ayaz Amin

Many tasks can be easily solved using machine learning techniques. However, some tasks cannot readily be solved using statistical models, requiring a symbolic approach instead. Program induction is one of the ways that s…

Program induction