schuderer / bprl

Business Process Control using Reinforcement Learning. Work in progress.
MIT License
3 stars 0 forks source link

Refactor out approximator #8

Closed schuderer closed 5 years ago

schuderer commented 5 years ago

Resolved #7. Refactored out a q-value approximator (ActionValueFunction) from the Agent, as well as separated out policies (currently inside the agent module: two python functions greedy() and epsilon_greedy()). The speed issues have been solved, and according to some comparisons the speed is the same as before the refactoring.