banditml / offline-policy-evaluation

Implementations and examples of common offline policy evaluation methods in Python.

banditml/offline-policy-evaluation Issues

Offline evaluation for slate recommendation
Updated 3 years ago
Confidence intervals on OPE estimates
Closed 3 years ago6
Support running OPE on batches
Updated 3 years ago
Implement More Robust Doubly Robust Method
Updated 3 years ago
KeyError: avg_order_size, which in features_config, yet not integrated into X in processor.py, but used at Line 207?
Closed 4 years ago2
Add UCB bandit using MDNs (mixture density networks)
Closed 4 years ago3