joshuaspear/offline_rl_ope

Stateful implementations of OPE algorithms, designed for use in the development of offline RL models

PythonMIT

Issues

Add targeted OPE measure
#11 opened 8 months ago by joshuaspear
0
Add array type checking
#10 opened 8 months ago by joshuaspear
0
Discounting aware importance sampling
#7 opened 8 months ago by joshuaspear
0
Epsilon smoothing for deterministic policies
#2 opened a year ago by joshuaspear
0