Bayesian Bellman Operators Matthew Fellows Kristian Hartikainen Shimon Whiteson Department of Computer Science University of Oxford
–Neural Information Processing Systems
We demonstrate that BootDQNprior+'s lagged target parameters, which are essential to its performance, arise from applying approximate inference to the BBO posterior.
Neural Information Processing Systems
Aug-15-2025, 03:46:00 GMT
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- Canada (0.04)
- United States
- Massachusetts
- Middlesex County > Cambridge (0.04)
- Hampshire County > Amherst (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Massachusetts
- Europe
- United Kingdom > England
- Oxfordshire > Oxford (0.40)
- Cambridgeshire > Cambridge (0.14)
- Sweden > Stockholm
- Stockholm (0.04)
- United Kingdom > England
- Asia > Middle East
- Jordan (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Oceania > Australia
- Genre:
- Research Report (0.93)