The Vision Group has worked on RL for robotics for some time, but recently also more theoretical works have been published. One of them is "Constrained Imitation Q-learning with Earth Mover’s Distance reward" that will be presented in the Deep Reinforcement Learning Workshop of the NeurIPS 2022 conference in December 9th 2022.
The following paper will be presented:
- Constrained Imitation Q-learning with Earth Mover’s Distance reward (W. Yang, N. Strokina, J. Pajarinen and J.-K. Kämäräinen), In Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) Workshop on Deep Reinforcement Learning, 2022.
The workshop Web site: