On the Complexity and Approximability of Optimal Sensor Selection for Mixed-Observable Markov Decision Processes.
Jayanth BhargavMahsa GhasemiShreyas SundaramPublished in: ACC (2023)
Keyphrases
- markov decision processes
- dynamic programming
- average cost
- average reward
- finite horizon
- action sets
- optimal policy
- state space
- reinforcement learning
- worst case
- finite state
- transition matrices
- discounted reward
- stationary policies
- reachability analysis
- decision theoretic planning
- infinite horizon
- total reward
- decision problems
- policy iteration
- risk sensitive
- planning under uncertainty
- model based reinforcement learning
- action space
- decision processes
- factored mdps
- state and action spaces
- partially observable
- reinforcement learning algorithms
- semi markov decision processes
- lower bound
- multistage
- markov decision process
- optimal control
- computational complexity
- monte carlo
- long run
- optimal strategy
- optimal solution