Evaluating Point-Based POMDP Solvers on Multicore Machines.
Guy ShaniPublished in: IEEE Trans. Syst. Man Cybern. Part B (2010)
Keyphrases
- point based value iteration
- reinforcement learning
- dynamical systems
- finite state
- belief state
- belief space
- learning machines
- partially observable markov decision process
- policy evaluation
- markov decision process
- partially observable markov decision processes
- machine learning
- sat solvers
- search strategies
- model free
- reward function
- shared memory
- markov decision processes
- monte carlo
- state space
- model free reinforcement learning