Inverse reinforcement learning (IRL) methods assume that the expert data is generated by an agent optimizing some reward function. However, in many settings, the agent may optimize a reward function subject to some constraints, where the constraints induce behaviors that may be otherwise difficult to express with just a reward function. We consider the setting where the reward function is given, and the constraints are unknown, and propose a method that is able to recover these constraints satisfactorily from the expert data. While previous work has focused on recovering hard constraints, our method can recover cumulative soft constraints that the agent satisfies on average per episode. In IRL fashion, our method solves this problem by adjusting the constraint function iteratively through a constrained optimization procedure, until the agent behavior matches the expert behavior. We demonstrate our approach on synthetic environments, robotics environments and real world highway driving scenarios.

When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify mathematically and unknown to the RL agents. To tackle these issues, Inverse Constrained Reinforcement Learning (ICRL) empirically estimates constraints from expert demonstrations. As an emerging research topic, ICRL does not have common benchmarks, and previous works tested algorithms under hand-crafted environments with manually-generated expert demonstrations. In this paper, we construct an ICRL benchmark in the context of RL application domains, including robot control, and autonomous driving. For each environment, we design relevant constraints and train expert agents to generate demonstration data. Besides, unlike existing baselines that learn a deterministic constraint, we propose a variational ICRL method to model a posterior distribution of candidate constraints. We conduct extensive experiments on these algorithms under our benchmark and show how they can facilitate studying important research challenges for ICRL. The benchmark, including the instructions for reproducing ICRL algorithms, is available at https://github.com/Guiliang/ICRL-benchmarks-public.

By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples. For their real-world deployments, detecting out-of-distribution (OOD) samples is essential. Assuming OOD to be outside the closed boundary of in-distribution, typical neural classifiers do not contain the knowledge of this boundary for OOD detection during inference. There have been recent approaches to instill this knowledge in classifiers by explicitly training the classifier with OOD samples close to the in-distribution boundary. However, these generated samples fail to cover the entire in-distribution boundary effectively, thereby resulting in a sub-optimal OOD detector. In this paper, we analyze the feasibility of such approaches by investigating the complexity of producing such "effective" OOD samples. We also propose a novel algorithm to generate such samples using a manifold learning network (e.g., variational autoencoder) and then train an n+1 classifier for OOD detection, where the $n+1^{th}$ class represents the OOD samples. We compare our approach against several recent classifier-based OOD detectors on MNIST and Fashion-MNIST datasets. Overall the proposed approach consistently performs better than the others.

--We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. T o aid the design process, in this work we decompose the design space with respect to important choices arising from the current state of the art approaches, and describe the resulting tradeoffs. In doing this, we also identify interesting directions of future work. In this work we consider the design space [1] of behaviour planning--high level decision making--for autonomous driving. To simplify the design process, we decompose the design space into three principal axes of design choices, based on our practical experience [2] and with reference to the current state of the art. Within each axis, we discuss the inevitable qualitative tradeoffs that exist and review the relevant literature. We illustrate our decomposition using feature diagrams [3]. In doing this, we identify potentially interesting areas of research within the behaviour planning design space. The motivation of our decomposition is as follows. Human driver control actions are continuous, yet driving also contains discrete episodes, arising from road connectivity, signs, signals, road-user interactions, etc.

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called "confident-classifier" by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and the uniform distribution (maximizing the entropy of the outputs). Thus, the samples could be detected as OOD if they have low confidence or high entropy. In this paper, we analyze this setting both theoretically and experimentally. We conclude that the resulting confident-classifier still yields arbitrarily high confidence for OOD samples far away from the in-distribution. We instead suggest training a classifier by adding an explicit "reject" class for OOD samples.

Machine learning can provide efficient solutions to the complex problems encountered in autonomous driving, but ensuring their safety remains a challenge. A number of authors have attempted to address this issue, but there are few publicly-available tools to adequately explore the trade-offs between functionality, scalability, and safety. We thus present WiseMove, a software framework to investigate safe deep reinforcement learning in the context of motion planning for autonomous driving. WiseMove adopts a modular learning architecture that suits our current research questions and can be adapted to new technologies and new questions. We present the details of WiseMove, demonstrate its use on a common traffic scenario, and describe how we use it in our ongoing safe learning research.