Relational Mimic for Visual Adversarial Imitation Learning
This work addresses the need for more robust and sample-efficient visual imitation learning methods, with potential applications in robotics and AI, though it appears incremental by building on existing generative adversarial imitation learning approaches.
The paper tackles imitation learning from video demonstrations by introducing Relational Mimic (RM), which combines generative adversarial networks and relational learning to improve robustness and sample efficiency, achieving higher performance in a challenging locomotion task with pixel inputs.
In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM is flexible and can be used in conjunction with other recent advances in generative adversarial imitation learning to better address the need for more robust and sample-efficient approaches. In addition, we introduce a new neural network architecture that improves upon the previous state-of-the-art in reinforcement learning and illustrate how increasing the relational reasoning capabilities of the agent enables the latter to achieve increasingly higher performance in a challenging locomotion task with pixel inputs. Finally, we study the effects and contributions of relational learning in policy evaluation, policy improvement and reward learning through ablation studies.