Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update
Su Young Lee, Choi Sungik, Sae-Young Chung
–Neural Information Processing Systems
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation.
Neural Information Processing Systems
Aug-20-2025, 07:38:02 GMT
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.14)
- North America > Canada (0.04)
- Europe > United Kingdom
- Industry:
- Leisure & Entertainment (0.46)
- Technology: