Proper Value Equivalence
–Neural Information Processing Systems
VE distinguishes models based on a set of policies and a set of functions: a model is said to be VE to the environment if the Bellman operators it induces for the policies yield the correct result when applied to the functions.
Neural Information Processing Systems
Nov-13-2025, 23:52:25 GMT
- Country:
- North America > United States
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Michigan (0.04)
- Massachusetts > Middlesex County
- North America > United States
- Genre:
- Research Report (0.46)
- Technology: