Meta Reinforcement Learning for Heuristic Planing.
Ricardo Luna GutierrezMatteo LeonettiPublished in: ICAPS (2021)
Keyphrases
- reinforcement learning
- dynamic programming
- optimal solution
- multi agent
- markov decision processes
- state space
- search algorithm
- function approximation
- simulated annealing
- temporal difference learning
- stochastic approximation
- policy search
- exploration strategy
- learning process
- mobile robot
- learning problems
- search strategies
- beam search
- robotic control