Login / Signup

Safe Policies for Reinforcement Learning via Primal-Dual Methods.

Santiago PaternainMiguel Calvo-FullanaLuiz F. O. ChamonAlejandro Ribeiro
Published in: IEEE Trans. Autom. Control. (2023)
Keyphrases
  • primal dual
  • reinforcement learning
  • semidefinite programming
  • learning algorithm
  • computational complexity
  • multiresolution
  • optimal policy
  • convex optimization problems
  • duality gap