We show how norms can be used to guide a reinforcement learning agent towards achieving normative behavior and apply the same set of norms over different domains. Thus, we are able to: (1) provide a way to intuitively encode social knowledge (through norms); (2) guide learning towards normative behaviors (through an automatic norm reward system); and (3) achieve a transfer of learning by abstracting policies; Finally, (4) the method is not dependent on a particular RL algorithm. We show how our approach can be seen as a means to achieve abstract representation and learn procedural knowledge based on the declarative semantics of norms and discuss possible implications of this in some areas of cognitive science. Index T erms --Norms, Institutions, Automatic Reward Shaping, Transfer of Learning, Abstract Policies, Abstraction, State-Space Selection, Schema I. I NTRODUCTION In order to be accepted in human society, robots need to comply with human social norms.

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of complex autonomous and other cyber-physical systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional Simplex approach, the advanced controller (AC) is treated as a black box; there are no techniques for correcting the AC after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses this limitation. NSA not only provides safety assurances for CPSs in the presence of a possibly faulty neural controller, but can also improve the safety of such a controller in an online setting via retraining, without degrading its performance. NSA also offers reverse switching strategies, which allow the AC to resume control of the system under reasonable conditions, allowing the mission to continue unabated. Our experimental results on several significant case studies, including a target-seeking ground rover navigating an obstacle field and a neural controller for an artificial pancreas system, demonstrate NSA's benefits.

Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.

Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control Tommy Tram 1, 2, 3, Ivo Batkovic 1, 2, 3, Mohammad Ali 1, and Jonas Sj oberg 2 Abstract -- In this paper, we propose a decision making algorithm intended for automated vehicles that negotiate with other possibly non-automated vehicles in intersections. The decision algorithm is separated into two parts: a high-level decision module based on reinforcement learning, and a low-level planning module based on model predictive control. Traffic is simulated with numerous predefined driver behaviors and intentions, and the performance of the proposed decision algorithm was evaluated against another controller . The results show that the proposed decision algorithm yields shorter training episodes and an increased performance in success rate compared to the other controller . Interactions between road users in intersections is a complex problem to solve, making it difficult to address using conventional rule based systems. Many advancements aim to solve this problem by trying to imitate human drivers [1] or predicting what other drivers in traffic are planning to do [2]. In [3], the authors show that by modeling the decision process as a partially observable Markov decision process, the model can account for uncertainty in sensing the environment and [4] showed some probabilistic guarantees when solving the problem using reinforcement learning (RL).

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques used to dupe classifiers in supervised learning. In contrast, this paper investigates the problem of devising optimal attacks, depending on a well-defined attacker's objective, e.g., to minimize the main agent average reward. When the policy and the system dynamics, as well as rewards, are known to the attacker, a scenario referred to as a white-box attack, designing optimal attacks amounts to solving a Markov Decision Process. For what we call black-box attacks, where neither the policy nor the system is known, optimal attacks can be trained using Reinforcement Learning techniques. Through numerical experiments, we demonstrate the efficiency of our attacks compared to existing attacks (usually based on Gradient methods). We further quantify the potential impact of attacks and establish its connection to the smoothness of the policy under attack. Smooth policies are naturally less prone to attacks (this explains why Lipschitz policies, with respect to the state, are more resilient). Finally, we show that from the main agent perspective, the system uncertainties and the attacker can be modeled as a Partially Observable Markov Decision Process. We actually demonstrate that using Reinforcement Learning techniques tailored to POMDP (e.g. using Recurrent Neural Networks) leads to more resilient policies.

We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are classified into one of k ranks, and use ideas from ordinal regression to find a reward function that maximizes the margin between the different ranks. This approach is based on the idea that agents should not only learn how to behave from experts, but also how not to behave from non-experts. We show there are MDPs where important differences in the reward function would be hidden from existing algorithms by the behaviour of the expert. Our method is particularly useful for problems where we have access to a large set of agent behaviours with varying degrees of expertise (such as through GPS or cellphones). We highlight the differences between our approach and existing methods using a simple grid domain and demonstrate its efficacy on determining passenger-finding strategies for taxi drivers, using a large dataset of GPS trajectories.

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions from expert demonstrations. Its extension to multi-agent settings, however, is difficult due to the more complex notions of rational behaviors. In this paper, we propose MA-AIRL, a new framework for multi-agent inverse reinforcement learning, which is effective and scalable for Markov games with high-dimensional state-action space and unknown dynamics. We derive our algorithm based on a new solution concept and maximum pseudolikelihood estimation within an adversarial reward learning framework. In the experiments, we demonstrate that MA-AIRL can recover reward functions that are highly correlated with ground truth ones, and significantly outperforms prior methods in terms of policy imitation.

Large multi-tenant production clusters often have to handle a variety of jobs and applications with a variety of complex resource usage characteristics. It is non-trivial and non-optimal to manually create placement rules for scheduling that would decide which applications should co-locate. In this paper, we present DeepPlace, a scheduler that learns to exploits various temporal resource usage patterns of applications using Deep Reinforcement Learning (Deep RL) to reduce resource competition across jobs running in the same machine while at the same time optimizing for overall cluster utilization.

Empowerment is an information-theoretic method that can be used to intrinsically motivate learning agents. It attempts to maximize an agent's control over the environment by encouraging visiting states with a large number of reachable next states. Empowered learning has been shown to lead to complex behaviors, without requiring an explicit reward signal. In this paper, we investigate the use of empowerment in the presence of an extrinsic reward signal. We hypothesize that empowerment can guide reinforcement learning (RL) agents to find good early behavioral solutions by encouraging highly empowered states. We propose a unified Bellman optimality principle for empowered reward maximization. Our empowered reward maximization approach generalizes both Bellman's optimality principle as well as recent information-theoretical extensions to it. We prove uniqueness of the empowered values and show convergence to the optimal solution. We then apply this idea to develop off-policy actor-critic RL algorithms for high-dimensional continuous domains. We experimentally validate our methods in robotics domains (MuJoCo). Our methods demonstrate improved initial and competitive final performance compared to model-free state-of-the-art techniques.

We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution (which may, for example, come from another policy). Different policies induce different distributions, so given an underlying metric, the Wasserstein distance quantifies how different policies are. This can be used to learn multiple polices which are different in terms of such Wasserstein distances by using a Wasserstein regulariser. Changing the sign of the regularisation parameter, one can learn a policy for which its trajectory mapping distribution is attracted to a given fixed distribution.