Distributional Reinforcement Learning on American Put Option (test)
0.4CVaR 1.0QR-iCVaR
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| QR-iCVaRalpha=0.22025.01 | 0.4 | 0.04 | -0.17 | 0 | 0.13 | 0.16 | 0.11 | |
| QR-SRMrisk measure parameter=ϕα=0.22025.01 | 0.56 | 0.21 | -0.21 | 0.05 | 0.29 | 0.24 | 0.17 | |
| QR-CVaRalpha=0.22025.01 | 0.64 | 0.24 | -0.27 | 0.05 | 0.33 | 0.26 | 0.19 | |
| QR-SRMrisk measure parameter=ϕα=0.52025.01 | 0.78 | 0.27 | -0.44 | 0 | 0.38 | 0.29 | 0.17 | |
| QR-CVaRalpha=0.52025.01 | 0.79 | 0.28 | -0.41 | 0.02 | 0.4 | 0.31 | 0.19 | |
| QR-iCVaRalpha=0.52025.01 | 0.82 | 0.14 | -0.36 | 0 | 0.32 | 0.33 | 0.23 | |
| QR-SRMrisk measure parameter=ϕλ=4.02025.01 | 0.84 | 0.28 | -0.37 | 0.05 | 0.42 | 0.35 | 0.23 | |
| QR-SRMrisk measure parameter=ϕν=2.02025.01 | 1.01 | 0.27 | -0.62 | -0.03 | 0.46 | 0.36 | 0.19 | |
| QR-SRMrisk measure parameter=ϕα2, w22025.01 | 1.06 | 0.26 | -0.57 | -0.01 | 0.47 | 0.4 | 0.24 | |
| QR-SRMrisk measure parameter=ϕα3, w32025.01 | 1.11 | 0.26 | -0.68 | -0.05 | 0.48 | 0.4 | 0.22 | |
| QR-DQN2025.01 | 1.4 | -0.24 | -1.76 | -0.67 | 0.21 | 0.16 | -0.18 | |
| QR-SRMrisk measure parameter=ϕα=1.02025.01 | 1.43 | 0.03 | -1.36 | -0.37 | 0.43 | 0.35 | 0.04 | |
| QR-CVaRalpha=1.02025.01 | 1.48 | -0.02 | -1.42 | -0.41 | 0.4 | 0.35 | 0.03 |