Reinforcement Learning with A* and a Deep Heuristic.
Ariel KeselmanSergey TenAdham GhazaliMajed JubehPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- dynamic programming
- function approximation
- learning algorithm
- genetic algorithm
- state space
- tabu search
- model free
- heuristic methods
- reinforcement learning algorithms
- beam search
- markov decision processes
- data sets
- simulated annealing
- policy search
- search algorithm
- optimal solution
- timetabling problem
- exploration strategy
- temporal difference
- robotic control
- transfer learning
- optimal control
- solution quality
- constraint satisfaction
- np hard
- learning process
- multi agent
- machine learning