search

rickstaa / stable-learning-control

A framework for training theoretically stable (and robust) Reinforcement Learning control algorithms.
https://rickstaa.dev/stable-learning-control
MIT License
6 stars 1 forks source link

fix: correct finite horizon buffer calculation #398

Closed rickstaa closed 7 months ago

rickstaa commented 7 months ago

This pull request addresses a bug in the FiniteHorizonReplayBuffer that resulted in an erroneous inclusion of an extra horizon step in the finite horizon reward computation.