Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning.
Hiroki FurutaTadashi KozunoTatsuya MatsushimaYutaka MatsuoShixiang Shane GuPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- function approximation
- adaptation process
- state space
- belief nets
- bayesian model
- model free
- optimal control
- learning capabilities
- multi agent systems
- inference process
- multi agent reinforcement learning
- markov decision processes
- belief networks
- probabilistic inference
- graphical models
- probabilistic reasoning
- dynamic bayesian networks
- supervised learning
- reinforcement learning algorithms
- multi agent
- bayesian networks