HUGO - Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach.
Malte LehnaClara HolzhüterSven TomfordeChristoph ScholzPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- dynamic programming
- search strategies
- function approximation
- optimal solution
- markov decision processes
- tabu search
- state space
- genetic algorithm
- heuristic search
- evolutionary algorithm
- training set
- search algorithm
- multi agent
- learning problems
- feasible solution
- learning algorithm
- data sets
- target detection
- model free
- temporal difference
- exploration strategy
- robotic control