Towards Learning to Imitate from a Single Video Demonstration
This addresses the challenge of imitation learning in real-world scenarios where only visual observations are available, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of enabling agents to learn imitation from a single video demonstration without access to state or action information, using contrastive training and a Siamese recurrent neural network to learn a reward function, and demonstrates that it outperforms state-of-the-art techniques in simulated environments.
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration. We use a Siamese recurrent neural network architecture to learn rewards in space and time between motion clips while training an RL policy to minimize this distance. Through experimentation, we also find that the inclusion of multi-task data and additional image encoding losses improve the temporal consistency of the learned rewards and, as a result, significantly improves policy learning. We demonstrate our approach on simulated humanoid, dog, and raptor agents in 2D and a quadruped and a humanoid in 3D. We show that our method outperforms current state-of-the-art techniques in these environments and can learn to imitate from a single video demonstration.