Density Ratio Learning
GradientDICE
Introduced by Zhang et al. in GradientDICE: Rethinking Generalized Offline Estimation of Stationary ValuesGradientDICE is a density ratio learning method for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. It optimizes a different objective from GenDICE by using the Perron-Frobenius theorem and eliminating GenDICE’s use of divergence, such that nonlinearity in parameterization is not necessary for GradientDICE, which is provably convergent under linear function approximation.
Source: GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
