# MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

@article{Pol2020MDPHN, title={MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning}, author={Elise van der Pol and Daniel E. Worrall and H. V. Hoof and Frans A. Oliehoek and M. Welling}, journal={ArXiv}, year={2020}, volume={abs/2006.16908} }

This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep reinforcement learning do not usually exploit knowledge about such structure. By building this prior knowledge into policy and value networks using an equivariance constraint, we can reduce the size of the solution space. We specifically focus on group-structured… CONTINUE READING

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 36 REFERENCES

Plannable Approximations to MDP Homomorphisms: Equivariance under Actions

- Mathematics, Computer Science
- 2020

4

Symmetry Learning for Function Approximation in Reinforcement Learning

- Mathematics, Computer Science
- 2017

7

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

- Computer Science, Mathematics
- 2018

85