Differentiable Quality Diversity

Quality diversity (QD) is a growing branch of stochastic optimization research that studies the problem of generating an archive of solutions that maximize a given objective function but are also diverse with respect to a set of specified measure functions. However, even when these functions are differentiable, QD algorithms treat them as "black boxes", ignoring gradient information. We present the differentiable quality diversity (DQD) problem, a special case of QD, where both the objective and measure functions are first order differentiable. We then present MAP-Elites via Gradient Arborescence (MEGA), a DQD algorithm that leverages gradient information to efficiently explore the joint range of the objective and measure functions. Results in two QD benchmark domains and in searching the latent space of a StyleGAN show that MEGA significantly outperforms state-of-the-art QD algorithms, highlighting DQD's promise for efficient quality diversity optimization when gradient information is available. Source code is available at https://github.com/icaros-usc/dqd.

Two-Stage Clustering of Human Preferences for Action Prediction in Assembly Tasks

To effectively assist human workers in assembly tasks a robot must proactively offer support by inferring their preferences in sequencing the task actions. Previous work has focused on learning the dominant preferences of human workers for simple tasks largely based on their intended goal. However, people may have preferences at different resolutions: they may share the same high-level preference for the order of the sub-tasks but differ in the sequence of individual actions. We propose a two-stage approach for learning and inferring the preferences of human operators based on the sequence of sub-tasks and actions. We conduct an IKEA assembly study and demonstrate how our approach is able to learn the dominant preferences in a complex task. We show that our approach improves the prediction of human actions through cross-validation. Lastly, we show that our two-stage approach improves the efficiency of task execution in an online experiment, and demonstrate its applicability in a real-world robot-assisted IKEA assembly.

Learning from Demonstrations using Signal Temporal Logic

Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions. However, it is susceptible to imperfections in demonstrations and also raises concerns of safety and interpretability in the learned control policies. To address these issues, we use Signal Temporal Logic to evaluate and rank the quality of demonstrations. Temporal logic-based specifications allow us to create non-Markovian rewards, and also define interesting causal dependencies between tasks such as sequential task specifications. We validate our approach through experiments on discrete-world and OpenAI Gym environments, and show that our approach outperforms the state-of-the-art Maximum Causal Entropy Inverse Reinforcement Learning.

A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy

The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applications. Exploring the diverse scenarios of interaction between humans and robots in simulation can improve understanding of the system and avoid potentially costly failures in real-world settings. We formulate this as a quality diversity (QD) problem, where the goal is to discover diverse failure scenarios by simultaneously exploring both environments and human actions. We focus on the shared autonomy domain, where the robot attempts to infer the goal of a human operator, and adopt the QD algorithm MAP-Elites to generate scenarios for two published algorithms in this domain: shared autonomy via hindsight optimization and linear policy blending. Some of the generated scenarios confirm previous theoretical findings, while others are surprising and bring about a new understanding of state-of-the-art implementations. Our experiments show that MAP-Elites outperforms Monte-Carlo simulation and optimization based methods in effectively searching the scenario space, highlighting its promise for automatic evaluation of algorithms in shared autonomy.

Video Game Level Repair via Mixed Integer Linear Programming

Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples. However, the generated levels are often unplayable without additional editing. We propose a generate-then-repair framework for automatic generation of playable levels adhering to specific styles. The framework constructs levels using a generative adversarial network (GAN) trained with human-authored examples and repairs them using a mixed-integer linear program (MIP) with playability constraints. A key component of the framework is computing minimum cost edits between the GAN generated level and the solution of the MIP solver, which we cast as a minimum cost network flow problem. Results show that the proposed framework generates a diverse range of playable levels, that capture the spatial relationships between objects exhibited in the human-authored levels.

Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network

Recent developments in machine learning techniques have allowed automatic generation of video game levels that are stylistically similar to human-designed examples. While the output of machine learning models such as generative adversarial networks (GANs) is notoriously hard to control, the recently proposed latent variable evolution (LVE) technique searches the space of GAN parameters to generate outputs that optimize some objective performance metric, such as level playability. However, the question remains on how to automatically generate a diverse range of high-quality solutions based on a prespecified set of desired characteristics. We introduce a new method called latent space illumination (LSI), which uses state-of-the-art quality diversity algorithms designed to optimize in continuous spaces, i.e., MAP-Elites with a directional variation operator and Covariance Matrix Adaptation MAP-Elites, to effectively search the parameter space of theGAN along a set of multiple level mechanics. We show the performance of LSI algorithms in three experiments in SuperMario Bros., a benchmark domain for procedural content generation. Results suggest that LSI generates sets of Mario levels that are reliably mechanically diverse as well as playable.

Robot Learning and Execution of Collaborative Manipulation Plans from YouTube Videos

People often watch videos on the web to learn how to cook new recipes, assemble furniture or repair a computer. We wish to enable robots with the very same capability. This is challenging; there is a large variation in manipulation actions and some videos even involve multiple persons, who collaborate by sharing and exchanging objects and tools. Furthermore, the learned representations need to be general enough to be transferable to robotic systems. Previous systems have enabled generation of semantic and human-interpretable robot commands in the form of visual sentences. However, they require manual selection of short action clips, which are then individually processed. We propose a framework for executing demonstrated action sequences from full-length, unconstrained videos on the web. The framework takes as input a video annotated with object labels and bounding boxes, and outputs a collaborative manipulation action plan for one or more robotic arms. We demonstrate the performance of the system in three full-length collaborative cooking videos on the web and propose an open-source platform for executing the learned plans in a simulation environment.

Fair Contextual Multi-Armed Bandits: Theory and Experiments

When an AI system interacts with multiple users, it frequently needs to make allocation decisions. For instance, a virtual agent decides whom to pay attention to in a group setting, or a factory robot selects a worker to deliver a part. Demonstrating fairness in decision making is essential for such systems to be broadly accepted. We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate that a task or a resource is assigned to a user. The proposed algorithm uses contextual information about the users and the task and makes no assumptions on how the losses capturing the performance of different users are generated. We provide theoretical guarantees of performance and empirical results from simulation and an online user study. The results highlight the benefit of accounting for contexts in fair decision making, especially when users perform better at some contexts and worse at others.

Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space

Quality Diversity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are a new class of population-based stochastic algorithms designed to generate a diverse collection of quality solutions. Meanwhile, variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are among the best-performing derivative-free optimizers in single-objective continuous domains. This paper proposes a new QD algorithm called Covariance Matrix Adaptation MAP-Elites (CMA-ME). Our new algorithm combines the dynamic self-adaptation techniques of CMA-ES with archiving and mapping techniques for maintaining diversity in QD. Results from experiments with standard continuous optimization benchmarks show that CMA-ME finds better-quality solutions than MAP-Elites; similarly, results on the strategic game Hearthstone show that CMA-ME finds both a higher overall quality and broader diversity of strategies than both CMA-ES and MAP-Elites. Overall, CMA-ME more than doubles the performance of MAP-Elites using standard QD performance metrics. These results suggest that QD algorithms augmented by operators from state-of-the-art optimization algorithms can yield high-performing methods for simultaneously exploring and optimizing continuous search spaces, with significant applications to design, testing, and reinforcement learning among other domains. Code is available for both the continuous optimization benchmark (https://github.com/tehqin/QualDivBenchmark) and Hearthstone (https://github.com/tehqin/EvoStone) domains.

Reinforcement Learning with Fairness Constraints for Resource Distribution in Human-Robot Teams

Much work in robotics and operations research has focused on optimal resource distribution, where an agent dynamically decides how to sequentially distribute resources among different candidates. However, most work ignores the notion of fairness in candidate selection. In the case where a robot distributes resources to human team members, disproportionately favoring the highest performing teammate can have negative effects in team dynamics and system acceptance. We introduce a multi-armed bandit algorithm with fairness constraints, where a robot distributes resources to human teammates of different skill levels. In this problem, the robot does not know the skill level of each human teammate, but learns it by observing their performance over time. We define fairness as a constraint on the minimum rate that each human teammate is selected throughout the task. We provide theoretical guarantees on performance and perform a large-scale user study, where we adjust the level of fairness in our algorithm. Results show that fairness in resource distribution has a significant effect on users' trust in the system.