Skip to content

Latest commit

 

History

History
12 lines (10 loc) · 341 Bytes

README.md

File metadata and controls

12 lines (10 loc) · 341 Bytes

rl

Library with implementations of different reinforcement learning algorithms

Implemented:

  • Deep Q learning (implemented with target network and experience replay)
  • Simulated annealing

Todo:

  • Genetic algorithm (in repo but not yet finished)
  • TRPO (trust region policy optimization)
  • CEM (cross-entropy method)
  • Advantage learning