Learning to Represent Action Values as a Hypergraph on the Action VerticesDownload PDF

Published: 12 Jan 2021, Last Modified: 05 May 2023ICLR 2021 PosterReaders: Everyone
Keywords: reinforcement learning, structural credit assignment, structural inductive bias, multi-dimensional discrete action spaces, learning action representations
Abstract: Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value can be learned. By viewing this problem through the lens of representation learning, good representations of both state and action can facilitate action-value estimation. While advances in deep learning have seamlessly driven progress in learning state representations, given the specificity of the notion of agency to RL, little attention has been paid to learning action representations. We conjecture that leveraging the combinatorial structure of multi-dimensional action spaces is a key ingredient for learning good representations of action. To test this, we set forth the action hypergraph networks framework---a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias. Using this framework we realise an agent class based on a combination with deep Q-networks, which we dub hypergraph Q-networks. We show the effectiveness of our approach on a myriad of domains: illustrative prediction problems under minimal confounding effects, Atari 2600 games, and discretised physical control benchmarks.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
One-sentence Summary: This paper introduces a class of models, called action hypergraph networks, for action-value estimation by leveraging the combinatorial structure of multi-dimensional discrete action spaces.
Code: [![github](/images/github_icon.svg) atavakol/action-hypergraph-networks](https://github.com/atavakol/action-hypergraph-networks)
Data: [Arcade Learning Environment](https://paperswithcode.com/dataset/arcade-learning-environment), [Box2D](https://paperswithcode.com/dataset/box2d), [DeepMind Control Suite](https://paperswithcode.com/dataset/deepmind-control-suite), [MuJoCo](https://paperswithcode.com/dataset/mujoco), [OpenAI Gym](https://paperswithcode.com/dataset/openai-gym), [PyBullet](https://paperswithcode.com/dataset/pybullet)
19 Replies