Reinforcement Learning in Sparse-Reward Environments With Hindsight Policy Gradients

DOI10.1162/neco_a_01387OpenAlexW3158799570MaRDI QIDQ5004371

Filipe Mutz, Paulo Rauber, Jürgen Schmidhuber, Avinash Ummadisingu

Publication date: 30 July 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://qmro.qmul.ac.uk/xmlui/handle/123456789/72285

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• Adam
• Baselines
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Model-based contextual policy search for data-efficient generalization of robot skills
• Q( $$\lambda $$ ) with Off-Policy Corrections
• Overcoming catastrophic forgetting in neural networks

This page was built for publication: Reinforcement Learning in Sparse-Reward Environments With Hindsight Policy Gradients