English

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

Machine Learning 2021-06-15 v1 Artificial Intelligence

Abstract

The Reinforcement Learning (RL) building blocks, i.e. Q-functions and policy networks, usually take elements from the cartesian product of two domains as input. In particular, the input of the Q-function is both the state and the action, and in multi-task problems (Meta-RL) the policy can take a state and a context. Standard architectures tend to ignore these variables' underlying interpretations and simply concatenate their features into a single vector. In this work, we argue that this choice may lead to poor gradient estimation in actor-critic algorithms and high variance learning steps in Meta-RL algorithms. To consider the interaction between the input variables, we suggest using a Hypernetwork architecture where a primary network determines the weights of a conditional dynamic network. We show that this approach improves the gradient approximation and reduces the learning step variance, which both accelerates learning and improves the final performance. We demonstrate a consistent improvement across different locomotion tasks and different algorithms both in RL (TD3 and SAC) and in Meta-RL (MAML and PEARL).

Keywords

Cite

@article{arxiv.2106.06842,
  title  = {Recomposing the Reinforcement Learning Building Blocks with Hypernetworks},
  author = {Shai Keynan and Elad Sarafian and Sarit Kraus},
  journal= {arXiv preprint arXiv:2106.06842},
  year   = {2021}
}

Comments

ICML 2021

R2 v1 2026-06-24T03:08:04.349Z