A Modified Memory-Based Reinforcement Learning Method for Solving POMDP Problems.
Lei ZhengSiu-Yeung ChoPublished in: Neural Process. Lett. (2011)
Keyphrases
- reinforcement learning
- significant improvement
- detection method
- quadratic programming
- solving problems
- similarity measure
- model free
- combinatorial optimization
- probabilistic model
- dynamic programming
- multi agent
- state space
- optimization problems
- np complete
- optimal policy
- markov decision processes
- cost function
- search methods
- optimal control
- computational complexity
- genetic algorithm
- markov decision process
- gradient method
- algebraic equations