Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update

Dec-26-2025, 02:31:23 GMT–Neural Information Processing Systems

We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation.

episodic backward update, name change, sample-efficient deep reinforcement learning, (1 more...)

Neural Information Processing Systems

Dec-26-2025, 02:31:23 GMT

Conferences Web Page

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)