Temporal Difference Learning on i.i.d. sampling
2Convergence RateBhandari et al., 2018
Evaluation results
| Method | Links | |
|---|---|---|
| Bhandari et al., 2018Step-size=1/√T, Parameters needed=None, Projection=No, Last or Average iterate convergence=Average2026.03 | 2 | |
| Bhandari et al., 2018Step-size=O(ω), Parameters needed=ω, Projection=No, Last or Average iterate convergence=Last2026.03 | 2 | |
| Bhandari et al., 2018Step-size=O(1/(1+tω)), Parameters needed=ω, Projection=No, Last or Average iterate convergence=Last2026.03 | 2 | |
| Samsonov et al., 2024Step-size=O(1), Parameters needed=None, Projection=No, Last or Average iterate convergence=Average2026.03 | 2 | |
| TD(0) with exponential step-sizeStep-size=O(1/T^{t/T}), Parameters needed=None, Projection=No, Last or Average iterate convergence=Last2026.03 | 2 | |
| Dalal et al., 2018Step-size=O(t + 1)^-z, z ∈ (0, 1), Parameters needed=None, Projection=No, Last or Average iterate convergence=Last2026.03 | 1 |