Heuristic-Guided Reinforcement Learning.
Ching-An ChengAndrey KolobovAdith SwaminathanPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- dynamic programming
- model free
- optimal solution
- search algorithm
- optimal policy
- markov decision processes
- learning algorithm
- beam search
- reinforcement learning algorithms
- simulated annealing
- autonomous learning
- stochastic approximation
- action space
- temporal difference
- heuristic methods
- learning problems
- supervised learning
- evolutionary algorithm
- learning process
- multi agent
- bayesian networks
- case study