Policy learning with partial observation and mechanical constraints for multi-person modeling.
Keisuke FujiiNaoya TakeishiYoshinobu KawaharaKazuya TakedaPublished in: CoRR (2020)
Keyphrases
- artificial neural networks
- learning algorithm
- prior knowledge
- online learning
- learning systems
- learning scheme
- reinforcement learning
- learning problems
- learning process
- inverse reinforcement learning
- supervised learning
- knowledge acquisition
- partially observable environments
- incremental learning
- learning scenarios
- learning tasks
- active learning
- case study