Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing.
Mogens Graf PlessenPublished in: CoRR (2017)
Keyphrases
- hill climbing
- reinforcement learning
- simulated annealing
- search space
- search algorithm
- genetic algorithm ga
- hill climbing algorithm
- search strategy
- systematic search
- search procedure
- direct search
- optimal policy
- max min
- path finding
- tabu search
- machine learning
- learning algorithm
- real time
- function approximation
- vehicle detection
- markov decision processes
- reinforcement learning algorithms
- steepest ascent
- model free
- rule learning
- hill climbing search
- state space
- genetic algorithm
- traffic flow
- beam search
- heuristic function
- transfer learning
- bayesian network structure learning
- heuristic search
- hybrid algorithms
- autonomous vehicles
- multi agent
- evolutionary algorithm
- dynamic programming
- action selection
- exhaustive search
- travel time
- temporal difference