Autonomous Selection of Inter-Task Mappings in Transfer Learning (extended abstract)
暂无分享,去创建一个
When transferring knowledge between reinforcement learning agents with different state representations or actions, past knowledge must be efficiently mapped so that it assists learning. The majority of the existing approaches use pre-defined mappings given by a domain expert. To overcome this limitations and allow autonomous transfer learning, this paper introduces a method for weighting and using multiple inter-task mappings, named COMBREL. Experimental results show that the use of multiple inter-task mappings, accompanied with a selection mechanism, can significantly boost the performance of transfer learning, relative to learning without transfer and relative to using a single hand-picked mapping.
[1] Peter Stone,et al. Transfer Learning via Inter-Task Mappings for Temporal Difference Learning , 2007, J. Mach. Learn. Res..
[2] Peter Stone,et al. Transferring Instances for Model-Based Reinforcement Learning , 2008, ECML/PKDD.
[3] Ioannis P. Vlahavas,et al. Transfer Learning via Multiple Inter-task Mappings , 2011, EWRL.
[4] Andrea Bonarini,et al. Transfer of samples in batch reinforcement learning , 2008, ICML '08.