multi-task policy
BAKU: AnEfficientTransformerfor Multi-TaskPolicyLearning
Inthiswork,wepresentBAKU,asimple transformer architecture that enables efficient learning of multi-task robot policies.BAKU builds upon recent advancements in offline imitation learning and meticulously combines observation trunks, action chunking, multi-sensory observations, and action heads tosubstantially improveupon prior work.
Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
Deep reinforcement learning (RL) is notoriously impractical to deploy due to sample inefficiency.
An Efficient Transformer for Multi-Task Policy Learning
Videos of the robot are best viewed at baku-robot.github.io.