Safe Policy Improvement for POMDPs via Finite-State Controllers.
Thiago D. SimãoMarnix SuilenNils JansenPublished in: CoRR (2023)
Keyphrases
- partially observable markov decision processes
- optimal policy
- policy search
- markov decision problems
- partially observable
- policy gradient
- reinforcement learning
- markov decision processes
- state space
- belief state
- infinite horizon
- finite state
- markov decision process
- expected reward
- dynamic programming
- point based value iteration
- search algorithm
- continuous state
- belief space
- decision processes
- finite horizon
- linear programming
- policy gradient methods