Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models.
Tiancheng ZhaoKaige XieMaxine EskénaziPublished in: CoRR (2019)
Keyphrases
- end to end
- action space
- latent variable models
- real valued
- reinforcement learning
- single agent
- action selection
- multi agent
- state and action spaces
- state space
- continuous state
- latent variables
- markov decision processes
- multiple agents
- multi agent systems
- dynamic environments
- learning problems
- stochastic processes
- function approximators
- hidden markov models
- function approximation
- hidden variables
- decision problems
- policy search
- latent dirichlet allocation
- markov decision process
- data mining
- machine learning