Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks
This addresses the need for adaptable imitation learning models in decision-making tasks where new tasks have limited or unlabeled data, though it is incremental as it builds on existing methods.
The paper tackles the problem of imitation learning being data-hungry and task-specific by proposing Meta-AIRL, which integrates meta-learning with adversarial inverse reinforcement learning to adapt policies and reward functions to new tasks with limited demonstrations, achieving performance comparable to experts on unseen tasks.
Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the model often fails to generalize to new tasks that have a different distribution. In practice, demonstrations from new tasks will be continuously observed and the data might be unlabeled or only partially labeled. Therefore, it is desirable for the trained model to adapt to new tasks that have limited data samples available. In this work, we build an adaptable imitation learning model based on the integration of Meta-learning and Adversarial Inverse Reinforcement Learning (Meta-AIRL). We exploit the adversarial learning and inverse reinforcement learning mechanisms to learn policies and reward functions simultaneously from available training tasks and then adapt them to new tasks with the meta-learning framework. Simulation results show that the adapted policy trained with Meta-AIRL can effectively learn from limited number of demonstrations, and quickly reach the performance comparable to that of the experts on unseen tasks.