Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge.
Naoki YokoyamaQian LuoDhruv BatraSehoon HaPublished in: IROS (2022)
Keyphrases
- learning process
- empirical studies
- multi agent systems
- learning algorithm
- cooperative
- machine learning methods
- learning models
- knowledge acquisition
- computational cost
- significant improvement
- machine learning
- inductive inference
- decision making
- human experts
- multiagent systems
- incomplete information
- multiple agents
- autonomous agents
- intelligent agents
- learning systems
- benchmark datasets
- dynamic environments
- reinforcement learning