As robots become ubiquitous in the workforce, it is essential that human-robot collaboration be both intuitive and adaptive. A robot's quality improves based on its ability to explicitly reason about the time-varying (i.e. learning curves) and stochastic capabilities of its human counterparts, and adjust the joint workload to improve efficiency while factoring human preferences. We introduce a novel resource coordination algorithm that enables robots to explore the relative strengths and learning abilities of their human teammates, by constructing schedules that are robust to stochastic and time-varying human task performance. We first validate our algorithmic approach using data we collected from a user study (n = 20), showing we can quickly generate and evaluate a robust schedule while discovering the latest individual worker proficiency. Second, we conduct a between-subjects experiment (n = 90) to validate the efficacy of our coordinating algorithm. Results from the human-subjects experiment indicate that scheduling strategies favoring exploration tend to be beneficial for human-robot collaboration as it improves team fluency (p = 0.0438), while also maximizing team efficiency (p < 0.001).

What happens when technology advancements threaten to automate people's jobs? That question is on the minds of many as research and development in artificial intelligence and machine learning rapidly advances. Recently ASU received a million dollar NSF Convergence Accelerator Grant to create autonomous systems that are not only more adaptable and efficient in manufacturing environments, but also have built-in adaptive tutoring systems that will cooperate with factory workers and retrain them to use AI technology so they are not displaced from their jobs. This multidisciplinary project is focused on using AI to augment the workplace rather than replace workers. The session will be live between 4:15 PM – 5: 10 PM ET.

Conflict-Based Search (CBS) is a popular framework for solving the Multi-Agent Path Finding problem. Some of the conflicts incur a foreseeable conflict in one or both of the children nodes when splitting on them. This paper introduces a new technique, namely the head-on technique that finds out such conflicts, so they can be processed more efficiently by resolving the conflict with the potential conflict all together in one split. The proposed technique applies to all CBS-based solvers. Experimental results show that the head-on technique improves the state-of-the-art MAPF solver CBSH.

In this contribution we study social network modelling by using human interaction as a basis. To do so, we propose a new set of functions, affinities, designed to capture the nature of the local interactions among each pair of actors in a network. By using these functions, we develop a new community detection algorithm, the Borgia Clustering, where communities naturally arise from the multi-agent interaction in the network. We also discuss the effects of size and scale for communities regarding this case, as well as how we cope with the additional complexity present when big communities arise. Finally, we compare our community detection solution with other representative algorithms, finding favourable results.

Voting rules may fail to implement the will of the society when only some voters actively participate, and/or in the presence of sybil (fake or duplicate) voters. Here we aim to address social choice in the presence of sybils and voter abstention. To do so we assume the status-quo (Reality) as an ever-present distinguished alternative, and study Reality Enforcing voting rules, which add virtual votes in support of the status-quo. We measure the tradeoff between safety and liveness (the ability of active honest voters to maintain/change the status-quo, respectively) in a variety of domains, and show that the Reality Enforcing voting rule is optimal in this respect.

Federated learning enables the development of a machine learning model among collaborating agents without requiring them to share their underlying data. However, malicious agents who train on random data, or worse, on datasets with the result classes inverted, can weaken the combined model. BlockFLow is an accountable federated learning system that is fully decentralized and privacy-preserving. Its primary goal is to reward agents proportional to the quality of their contribution while protecting the privacy of the underlying datasets and being resilient to malicious adversaries. Specifically, BlockFLow incorporates differential privacy, introduces a novel auditing mechanism for model contribution, and uses Ethereum smart contracts to incentivize good behavior. Unlike existing auditing and accountability methods for federated learning systems, our system does not require a centralized test dataset, sharing of datasets between the agents, or one or more trusted auditors; it is fully decentralized and resilient up to a 50% collusion attack in a malicious trust model. When run on the public Ethereum blockchain, BlockFLow uses the results from the audit to reward parties with cryptocurrency based on the quality of their contribution. We evaluated BlockFLow on two datasets that offer classification tasks solvable via logistic regression models. Our results show that the resultant auditing scores reflect the quality of the honest agents' datasets. Moreover, the scores from dishonest agents are statistically lower than those from the honest agents. These results, along with the reasonable blockchain costs, demonstrate the effectiveness of BlockFLow as an accountable federated learning system.

There has been recent interest in collaborative multi-agent bandits, where groups of agents share recommendations to decrease per-agent regret. However, these works assume that each agent always recommends their individual best-arm estimates to other agents, which is unrealistic in envisioned applications (machine faults in distributed computing or spam in social recommendation systems). Hence, we generalize the setting to include honest and malicious agents who recommend best-arm estimates and arbitrary arms, respectively. We show that even with a single malicious agent, existing collaboration-based algorithms fail to improve regret guarantees over a single-agent baseline. We propose a scheme where honest agents learn who is malicious and dynamically reduce communication with them, i.e., "blacklist" them. We show that collaboration indeed decreases regret for this algorithm, when the number of malicious agents is small compared to the number of arms, and crucially without assumptions on the malicious agents' behavior. Thus, our algorithm is robust against any malicious recommendation strategy.

Federated Learning (FL) allows a set of agents to collaboratively train a model in a decentralized fashion without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One important line of attacks against FL is the backdoor attacks. In a backdoor attack, an adversary tries to embed a backdoor trigger functionality to the model during training which can later be activated to cause a desired misclassification. To prevent such backdoor attacks, we propose a lightweight defense that requires no change to the FL structure. At a high level, our defense is based on carefully adjusting the server's learning rate, per dimension, at each round based on the sign information of agent's updates. We first conjecture the necessary steps to carry a successful backdoor attack in FL setting, and then, explicitly formulate the defense based on our conjecture. Through experiments, we provide empirical evidence to the support of our conjecture. We test our defense against backdoor attacks under different settings, and, observe that either backdoor is completely eliminated, or its accuracy is significantly reduced. Overall, our experiments suggests that our approach significantly outperforms some of the recently proposed defenses in the literature. We achieve this by having minimal influence over the accuracy of the trained models.

Federated Learning (FL) has become a popular paradigm for learning from distributed data. To effectively utilize data at different devices without moving them to the cloud, algorithms such as the Federated Averaging (FedAvg) have adopted a "computation then aggregation" (CTA) model, in which multiple local updates are performed using local data, before sending the local models to the cloud for aggregation. However, these schemes typically require strong assumptions, such as the local data are identically independent distributed (i.i.d), or the size of the local gradients are bounded. In this paper, we first explicitly characterize the behavior of the FedAvg algorithm, and show that without strong and unrealistic assumptions on the problem structure, the algorithm can behave erratically for non-convex problems (e.g., diverge to infinity). Aiming at designing FL algorithms that are provably fast and require as few assumptions as possible, we propose a new algorithm design strategy from the primal-dual optimization perspective. Our strategy yields a family of algorithms that take the same CTA model as existing algorithms, but they can deal with the non-convex objective, achieve the best possible optimization and communication complexity while being able to deal with both the full batch and mini-batch local computation models. Most importantly, the proposed algorithms are {\it communication efficient}, in the sense that the communication pattern can be adaptive to the level of heterogeneity among the local data. To the best of our knowledge, this is the first algorithmic framework for FL that achieves all the above properties.

Standard RL algorithms assume fixed environment dynamics and require a significant amount of interaction to adapt to new environments. We introduce Policy-Dynamics Value Functions (PD-VF), a novel approach for rapidly adapting to dynamics different from those previously seen in training. PD-VF explicitly estimates the cumulative reward in a space of policies and environments. An ensemble of conventional RL policies is used to gather experience on training environments, from which embeddings of both policies and environments can be learned. Then, a value function conditioned on both embeddings is trained. At test time, a few actions are sufficient to infer the environment embedding, enabling a policy to be selected by maximizing the learned value function (which requires no additional environment interaction). We show that our method can rapidly adapt to new dynamics on a set of MuJoCo domains. Code available at https://github.com/rraileanu/policy-dynamics-value-functions.