General value function networks

DOI10.1613/JAIR.1.12105MaRDI QIDQ5856468zbMATH OpenOpenAlexFDO

Authors Matthew Schlegel, Andrew Jacobsen, Andrew Patterson, Adam White, Martha White, Z. Abbas

Publication date 26 March 2021

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.06763

zbMATH Keywords

neural networksreinforcement learning

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Recurrent policy gradients
• scientific article; zbMATH DE number 1843097
• Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains
• Task-aware verifiable RNN-based policies for partially observable Markov decision processes
• Efficient reinforcement learning in deterministic systems with value function generalization

Cites work

• A spectral algorithm for learning hidden Markov models
• scientific article; zbMATH DE number 786738 (Why is no real title available?)
• Neural networks and physical systems with emergent collective computational abilities
• Planning and acting in partially observable stochastic domains
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains

Cited in

(1)

• Recurrent policy gradients

Describes a project that uses

Uses Software

• IMPALA

This page was built for publication: General value function networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5856468)