Deep Adaptive Multi-Intention Inverse Reinforcement Learning
This work addresses the challenge of modeling multi-intention behaviors in robotics and AI, though it is incremental as it builds on prior IRL methods with adaptive intention inference.
The paper tackles the problem of learning an unknown number of nonlinear reward functions from unlabeled expert demonstrations in inverse reinforcement learning, achieving improved performance over existing baselines on three benchmarks.
This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn an a priori unknown number of nonlinear reward functions from unlabeled experts' demonstrations. For this purpose, we employ the tools from Dirichlet processes and propose an adaptive approach to simultaneously account for both complex and unknown number of reward functions. Using the conditional maximum entropy principle, we model the experts' multi-intention behaviors as a mixture of latent intention distributions and derive two algorithms to estimate the parameters of the deep reward network along with the number of experts' intentions from unlabeled demonstrations. The proposed algorithms are evaluated on three benchmarks, two of which have been specifically extended in this study for multi-intention IRL, and compared with well-known baselines. We demonstrate through several experiments the advantages of our algorithms over the existing approaches and the benefits of online inferring, rather than fixing beforehand, the number of expert's intentions.