TY - CPAPER AB - 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 ofrepresentation learning, good representations of both state and action can facilitateaction-value estimation. While advances in deep learning have seamlessly drivenprogress in learning state representations, given the specificity of the notion ofagency to RL, little attention has been paid to learning action representations. Weconjecture that leveraging the combinatorial structure of multi-dimensional actionspaces 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 forlearning action representations in multi-dimensional discrete action spaces with astructural inductive bias. Using this framework we realise an agent class basedon a combination with deep Q-networks, which we dub hypergraph Q-networks.We show the effectiveness of our approach on a myriad of domains: illustrativeprediction problems under minimal confounding effects, Atari 2600 games, anddiscretised physical control benchmarks. AU - Tavakoli,A AU - Fatemi,M AU - Kormushev,P PY - 2021/// TI - Learning to represent action values as a hypergraph on the action vertices UR - http://kormushev.com/papers/Tavakoli_ICLR-2021.pdf ER -