Multi-Horizon Learning in Procedurally-Generated Environments for Off-Policy Reinforcement Learning (Student Abstract).
Raja Farrukh AliKevin DuongNasik Muhammad NafiWilliam H. HsuPublished in: AAAI (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- learning agents
- computer programming
- learning tasks
- active learning
- supervised learning
- reinforcement learning methods
- function approximation
- learning analytics
- online learning
- learning experience
- optimal policy
- online course
- learning capabilities
- learning styles
- learning gains
- state space
- university level
- policy search