Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning.
Christian GeishauserCarel van NiekerkNurul LubisMichael HeckHsien-Chin LinShutong FengMilica GasicPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- function approximation
- action selection
- fault diagnosis
- partially observable
- machine learning
- markov decision processes
- approximate dynamic programming
- function approximators
- fuzzy logic
- state space
- multi agent
- power system
- action space
- learning process
- actor critic
- state and action spaces