Sciweavers

Share
NIPS
2004

Responding to Modalities with Different Latencies

9 years 22 days ago
Responding to Modalities with Different Latencies
Motor control depends on sensory feedback in multiple modalities with different latencies. In this paper we consider within the framework of reinforcement learning how different sensory modalities can be combined and selected for real-time, optimal movement control. We propose an actor-critic architecture with multiple modules, whose output are combined using a softmax function. We tested our architecture in a simulation of a sequential reaching task. Reaching was initially guided by visual feedback with a long latency. Our learning scheme allowed the agent to utilize the somatosensory feedback with shorter latency when the hand is near the experienced trajectory. In simulations with different latencies for visual and somatosensory feedback, we found that the agent depended more on feedback with shorter latency.
Fredrik Bissmarck, Hiroyuki Nakahara, Kenji Doya,
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors Fredrik Bissmarck, Hiroyuki Nakahara, Kenji Doya, Okihide Hikosaka
Comments (0)
books