Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement LearningDownload PDF

29 Sept 2021, 00:34 (modified: 15 Mar 2022, 12:21)ICLR 2022 PosterReaders: Everyone
Keywords: Multitask Reinforcement Learning, Modular Reinforcement Learning, Transfer Learning, Transformer, Structural Embedding
Abstract: Modular Reinforcement Learning, where the agent is assumed to be morphologically structured as a graph, for example composed of limbs and joints, aims to learn a policy that is transferable to a structurally similar but different agent. Compared to traditional Multi-Task Reinforcement Learning, this promising approach allows us to cope with inhomogeneous tasks where the state and action space dimensions differ across tasks. Graph Neural Networks are a natural model for representing the pertinent policies, but a recent work has shown that their multi-hop message passing mechanism is not ideal for conveying important information to other modules and thus a transformer model without morphological information was proposed. In this work, we argue that the morphological information is still very useful and propose a transformer policy model that effectively encodes such information. Specifically, we encode the morphological information in terms of the traversal-based positional embedding and the graph-based relational embedding. We empirically show that the morphological information is crucial for modular reinforcement learning, substantially outperforming prior state-of-the-art methods on multi-task learning as well as transfer learning settings with different state and action space dimensions.
One-sentence Summary: We present a modular Multi-task Reinforcement Learning method for inhomogeneous control tasks incorporating structural embedding of morphology.
13 Replies