Table 2. Model recovery.
Comparison model | |||||
---|---|---|---|---|---|
TD | RSTD | FourLR | Utility | ||
Generating model | TD | - | 0.98 | 1.00 | 0.97 |
RSTD | 0.57 | - | 0.99 | 0.65 | |
FourLR | 0.50 | 0.31 | - | 0.39 | |
Utility | 0.58 | 0.76 | 0.99 | - |
TD, temporal difference; RSTD, risk-sensitive temporal difference; LR, learning rate.