Imitation Learning (IL) has been successfully applied to complex sequential decision-making problems where standard Reinforcement Learning (RL) algorithms fail. A number of recent methods extend IL to few-shot learning scenarios, where a meta-trained policy learns to quickly master new tasks using limited demonstrations. However, although Inverse Reinforcement Learning (IRL) often outperforms Behavioral Cloning (BC) in terms of imitation quality, most of these approaches build on BC due to its simple optimization objective. In this work, we propose SMILe, a scalable framework for Meta Inverse Reinforcement Learning (Meta-IRL) based on maximum entropy IRL, which can learn high-quality policies from few demonstrations. We examine the efficacy of our method on a variety of high-dimensional simulated continuous control tasks and observe that SMILe significantly outperforms Meta-BC. To our knowledge, our approach is the first efficient method for Meta-IRL that scales to the intractable function approximator setting.

In many settings, it is desirable to learn decision-making and control policies through learning or from expert demonstrations. The most common approaches under this framework are Behaviour Cloning (BC), and Inverse Reinforcement Learning (IRL). Recent methods for IRL have demonstrated the capacity to learn effective policies with access to a very limited set of demonstrations, a scenario in which BC methods often fail. Unfortunately, directly comparing the algorithms for these methods does not provide adequate intuition for understanding this difference in performance. This is the motivating factor for our work. We begin by presenting $f$-MAX, a generalization of AIRL (Fu et al., 2018), a state-of-the-art IRL method. $f$-MAX provides grounds for more directly comparing the objectives for LfD. We demonstrate that $f$-MAX, and by inheritance AIRL, is a subset of the cost-regularized IRL framework laid out by Ho & Ermon (2016). We conclude by empirically evaluating the factors of difference between various LfD objectives in the continuous control domain.

Neural networks can learn relevant features from data, but their predictive accuracy and propensity to overfit are sensitive to the values of the discrete hyperparameters that specify the network architecture (number of hidden layers, number of units per layer, etc.). Previous work optimized these hyperparmeters via grid search, random search, and black box optimization techniques such as Bayesian optimization. Bolstered by recent advances in gradient-based optimization of discrete stochastic objectives, we instead propose to directly model a distribution over possible architectures and use variational optimization to jointly optimize the network architecture and weights in one training pass. We discuss an implementation of this approach that estimates gradients via the Concrete relaxation, and show that it finds compact and accurate architectures for convolutional neural networks applied to the CIFAR10 and CIFAR100 datasets.