Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning.
Daniele RedaTianxin TaoMichiel van de PannePublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning systems
- deeper understanding
- learning problems
- dynamic environments
- autonomous robots
- hybrid learning
- markov decision processes
- online learning
- supervised learning
- collaborative learning environment
- learning capabilities
- learning agent
- sensory data
- deep architectures
- design principles
- design process
- state space
- mobile robot
- active learning
- user interface
- case study