Various implementations of Deep Reinforcement Learning (RL) demonstrated excellent performance on tasks that can be solved by trained policy, but they are not without drawbacks. Deep RL suffers from high sensitivity to noisy and missing input and adversarial attacks. To mitigate these deficiencies of deep RL solutions, we suggest involving spiking neural networks (SNNs). Previous work has shown that standard Neural Networks trained using supervised learning for image classification can be converted to SNNs with negligible deterioration in performance. In this paper, we convert Q-Learning ReLU-Networks (ReLU-N) trained using reinforcement learning into SNN. We provide a proof of concept for the conversion of ReLU-N to SNN demonstrating improved robustness to occlusion and better generalization than the original ReLU-N. Moreover, we show promising initial results with converting full-scale Deep Q-networks to SNNs, paving the way for future research.

Recently, there have been several high-profile achievements of agents learning to play games against humans and beat them. We consider an alternative approach that instead addresses game design for a better player experience by training human-like game agents. Specifically, we study the problem of training game agents in service of the development processes of the game developers that design, build, and operate modern games. We highlight some of the ways in which we think intelligent agents can assist game developers to understand their games, and even to build them. Our early results using the proposed agent framework mark a few steps toward addressing the unique challenges that game developers face.

We examine the problem of adversarial reinforcement learning for multi-agent domains including a rule-based agent. Rule-based algorithms are required in safety-critical applications for them to work properly in a wide range of situations. Hence, every effort is made to find failure scenarios during the development phase. However, as the software becomes complicated, finding failure cases becomes difficult. Especially in multi-agent domains, such as autonomous driving environments, it is much harder to find useful failure scenarios that help us improve the algorithm. We propose a method for efficiently finding failure scenarios; this method trains the adversarial agents using multi-agent reinforcement learning such that the tested rule-based agent fails. We demonstrate the effectiveness of our proposed method using a simple environment and autonomous driving simulator.

In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive and time consuming. Autoencoders are deep neural network used to compress high dimensional data such as pixelated images into small latent representations. This compression model is vital to efficiently learn policies, especially when learning on embedded systems. We have implemented this model on the NVIDIA Jetson TX2 embedded GPU, and evaluated the power consumption, throughput, and energy consumption of the autoencoders for various CPU/GPU core combinations, frequencies, and model parameters. Additionally, we have shown the reconstructions generated by the autoencoder to analyze the quality of the generated compressed representation and also the performance of the reinforcement learning agent. Finally, we have presented an assessment of the viability of training these models on embedded systems and their usefulness in developing autonomous policies. Using autoencoders, we were able to achieve 4-5 $\times$ improved performance compared to a baseline RL agent with a convolutional feature extractor, while using less than 2W of power.

We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that estimate feature expectations in an off-policy setting and a transition-regularized imitation network that produces a near-expert initial policy and an efficient feature representation. Our algorithm achieves superior results in batch settings on both control benchmarks and a vital clinical task of sepsis management in the Intensive Care Unit.

Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combine temporal logic with control Lyapunov functions to improve exploration. We incorporate control barrier functions to safeguard the exploration and deployment process. We develop a flexible and learnable system that allows users to specify task objectives and constraints in different forms and at various levels. The framework is also able to take advantage of known system dynamics and handle unknown environmental dynamics by integrating model-free learning with model-based planning.

Reinforcement learning algorithms can be used to optimally solve dynamic decision-making and control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis function expansions, have two main drawbacks: they are black-box models offering no insight in the mappings learned, and they require significant trial and error tuning of their meta-parameters. In this paper, we propose a new approach to constructing smooth value functions by means of symbolic regression. We introduce three off-line methods for finding value functions based on a state transition model: symbolic value iteration, symbolic policy iteration, and a direct solution of the Bellman equation. The methods are illustrated on four nonlinear control problems: velocity control under friction, one-link and two-link pendulum swing-up, and magnetic manipulation. The results show that the value functions not only yield well-performing policies, but also are compact, human-readable and mathematically tractable. This makes them potentially suitable for further analysis of the closed-loop system. A comparison with alternative approaches using neural networks shows that our method constructs well-performing value functions with substantially fewer parameters.

We introduce a novel implementation of a reinforcement learning (RL) algorithm which is designed to find an optimal jet grooming strategy, a critical tool for collider experiments. The RL agent is trained with a reward function constructed to optimize the resulting jet properties, using both signal and background samples in a simultaneous multi-level training. We show that the grooming algorithm derived from the deep RL agent can match state-of-the-art techniques used at the Large Hadron Collider, resulting in improved mass resolution for boosted objects. Given a suitable reward function, the agent learns how to train a policy which optimally removes soft wide-angle radiation, allowing for a modular grooming technique that can be applied in a wide range of contexts. These results are accessible through the corresponding GroomRL framework.

Machine learning has been applied to a number of creative, design-oriented tasks. However, it remains unclear how to best empower human users with these machine learning approaches, particularly those users without technical expertise. In this paper we propose a general framework for turn-based interaction between human users and AI agents designed to support human creativity, called {co-creative systems}. The framework can be used to better understand the space of possible designs of co-creative systems and reveal future research directions. We demonstrate how to apply this framework in conjunction with a pair of recent human subject studies, comparing between the four human-AI systems employed in these studies and generating hypotheses towards future studies.

We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanation type, reward-decomposition bars (predictions of future types of rewards). We designed a 124 participant, four-treatment experiment to compare participants' mental models of an RL agent in a simple Real-Time Strategy (RTS) game. Our results show that the combination of both saliency and reward bars were needed to achieve a statistically significant improvement in mental model score over the control. In addition, our qualitative analysis of the data reveals a number of effects for further study.