Forward-Backward Reinforcement Learning.
Ashley D. EdwardsLaura DownsJames C. DavidsonPublished in: CoRR (2018)
Keyphrases
- forward backward
- reinforcement learning
- hidden markov models
- function approximation
- state space
- learning algorithm
- markov decision processes
- control problems
- temporal difference
- machine learning
- reinforcement learning algorithms
- optimal policy
- direct policy search
- perceptual aliasing
- autonomous learning
- real time
- multi agent
- neural network
- data sets
- model free
- least squares
- dynamic programming
- search algorithm
- markov decision process
- function approximators
- knowledge base
- partially observable domains