Login / Signup

On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP.

Huizhen YuDimitri P. Bertsekas
Published in: Math. Oper. Res. (2008)
Keyphrases
  • average cost
  • finite state
  • optimal policy
  • markov decision processes
  • reinforcement learning
  • optimal control
  • long run
  • computational complexity
  • linear programming
  • dynamical systems
  • belief state