Machine learning algorithms are increasingly used to make or support decisions in a wide range of settings. With such expansive use there is also growing concern about the fairness of such methods. Prior literature on algorithmic fairness has extensively addressed risks and in many cases presented approaches to manage some of them. However, most studies have focused on fairness issues that arise from actions taken by a (single) focal decision-maker or agent. In contrast, most real-world systems have many agents that work collectively as part of a larger ecosystem. For example, in a lending scenario, there are multiple lenders who evaluate loans for applicants, along with policymakers and other institutions whose decisions also affect outcomes. Thus, the broader impact of any lending decision of a single decision maker will likely depend on the actions of multiple different agents in the ecosystem. This paper develops formalisms for firm versus systemic fairness, and calls for a greater focus in the algorithmic fairness literature on ecosystem-wide fairness - or more simply systemic fairness - in real-world contexts.

This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing techniques such as averaging the q-values or the updates on the mean-field distribution. This work presents a different approach to stabilize the learning based on proximal updates on the mean-field policy. We name our algorithm Mean Field Proximal Policy Optimization (MF-PPO), and we empirically show the effectiveness of our method in the OpenSpiel framework.

AI-powered robots are generally trained in simulation environments before they are tested and introduced in real-world settings. These environments allow developers to safely test their machine learning techniques on a variety of robots and in numerous possible scenarios, without having to purchase hardware, assemble robots and then bring them to remote locations, or compromise on real-world safety of the deployed systems. Amazon Alexa AI recently created a new simulation platform specifically for embodied AI research, the field specialized in the development of autonomous robots. This platform, dubbed Alexa Arena, was presented in a paper pre-published on arXiv and is publicly available on GitHub. "Our primary objective was to develop an interactive Embodied AI framework to catalyze the creation of next-generation embodied AI agents," Govind Thattai, the lead scientist for Arena platform, told Tech Xplore.

In recent months, we have seen the emergence and proliferation of several artificial intelligence systems worldwide, such as OpenAI's ChatGPT, GPT-4, and Google's Bard. Microsoft's new Bing and Baidu's Ernie Bot have also entered the scene. Joining this group of AI systems is a newcomer known as BabyAGI. BabyAGI is an innovative AI platform designed to train and evaluate various AI agents in a simulated environment. The AI is a pared-down version of the original Task-Driven Autonomous Agent developed and launched by VC and AI expert Yohei Nakajima.

Finding a balance between collaboration and competition is crucial for artificial agents in many real-world applications. We investigate this using a Multi-Agent Reinforcement Learning (MARL) setup on the back of a high-impact problem. The accumulation and yearly growth of plastic in the ocean cause irreparable damage to many aspects of oceanic health and the marina system. To prevent further damage, we need to find ways to reduce macroplastics from known plastic patches in the ocean. Here we propose a Graph Neural Network (GNN) based communication mechanism that increases the agents' observation space. In our custom environment, agents control a plastic collecting vessel. The communication mechanism enables agents to develop a communication protocol using a binary signal. While the goal of the agent collective is to clean up as much as possible, agents are rewarded for the individual amount of macroplastics collected. Hence agents have to learn to communicate effectively while maintaining high individual performance. We compare our proposed communication mechanism with a multi-agent baseline without the ability to communicate. Results show communication enables collaboration and increases collective performance significantly. This means agents have learned the importance of communication and found a balance between collaboration and competition.

Modern multi-agent reinforcement learning (RL) algorithms hold great potential for solving a variety of real-world problems. However, they do not fully exploit cross-agent knowledge to reduce sample complexity and improve performance. Although transfer RL supports knowledge sharing, it is hyperparameter sensitive and complex. To solve this problem, we propose a novel multi-agent policy reciprocity (PR) framework, where each agent can fully exploit cross-agent policies even in mismatched states. We then define an adjacency space for mismatched states and design a plug-and-play module for value iteration, which enables agents to infer more precise returns. To improve the scalability of PR, deep PR is proposed for continuous control tasks. Moreover, theoretical analysis shows that agents can asymptotically reach consensus through individual perceived rewards and converge to an optimal value function, which implies the stability and effectiveness of PR, respectively. Experimental results on discrete and continuous environments demonstrate that PR outperforms various existing RL and transfer RL methods.

It is desirable to predict the behavior of traffic participants conditioned on different planned trajectories of the autonomous vehicle. This allows the downstream planner to estimate the impact of its decisions. Recent approaches for conditional behavior prediction rely on a regression decoder, meaning that coordinates or polynomial coefficients are regressed. In this work we revisit set-based trajectory prediction, where the probability of each trajectory in a predefined trajectory set is determined by a classification model, and first-time employ it to the task of conditional behavior prediction. We propose RESET, which combines a new metric-driven algorithm for trajectory set generation with a graph-based encoder. For unconditional prediction, RESET achieves comparable performance to a regression-based approach. Due to the nature of set-based approaches, it has the advantageous property of being able to predict a flexible number of trajectories without influencing runtime or complexity. For conditional prediction, RESET achieves reasonable results with late fusion of the planned trajectory, which was not observed for regression-based approaches before. This means that RESET is computationally lightweight to combine with a planner that proposes multiple future plans of the autonomous vehicle, as large parts of the forward pass can be reused.

This paper proposes a novel distributed coverage controller for a multi-agent system with constant-speed unicycle robots (CSUR). The work is motivated by the limitation of the conventional method that does not ensure the satisfaction of hard state- and input-dependent constraints and leads to feasibility issues for multi-CSUR systems. In this paper, we solve these problems by designing a novel coverage cost function and a saturated gradient-search-based control law. Invariant set theory and Lyapunov-based techniques are used to prove the state-dependent confinement and the convergence of the system state to the optimal coverage configuration, respectively. The controller is implemented in a distributed manner based on a novel communication standard among the agents. A series of simulation case studies are conducted to validate the effectiveness of the proposed coverage controller in different initial conditions and with control parameters. A comparison study in simulation reveals the advantage of the proposed method in terms of avoiding infeasibility. The experiment study verifies the applicability of the method to real robots with uncertainties. The development procedure of the method from theoretical analysis to experimental validation provides a novel framework for multi-agent system coordinate control with complex agent dynamics.

We present hierarchical policy blending as optimal transport (HiPBOT). HiPBOT hierarchically adjusts the weights of low-level reactive expert policies of different agents by adding a look-ahead planning layer on the parameter space. The high-level planner renders policy blending as unbalanced optimal transport consolidating the scaling of the underlying Riemannian motion policies. As a result, HiPBOT effectively decides the priorities between expert policies and agents, ensuring the task's success and guaranteeing safety. Experimental results in several application scenarios, from low-dimensional navigation to high-dimensional whole-body control, show the efficacy and efficiency of HiPBOT. Our method outperforms state-of-the-art baselines -- either adopting probabilistic inference or defining a tree structure of experts -- paving the way for new applications of optimal transport to robot control. More material at https://sites.google.com/view/hipobot

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, current LfD frameworks are not capable of fast adaptation to heterogeneous human demonstrations nor the large-scale deployment in ubiquitous robotics applications. In this paper, we propose a novel LfD framework, Fast Lifelong Adaptive Inverse Reinforcement learning (FLAIR). Our approach (1) leverages learned strategies to construct policy mixtures for fast adaptation to new demonstrations, allowing for quick end-user personalization, (2) distills common knowledge across demonstrations, achieving accurate task inference; and (3) expands its model only when needed in lifelong deployments, maintaining a concise set of prototypical strategies that can approximate all behaviors via policy mixtures. We empirically validate that FLAIR achieves adaptability (i.e., the robot adapts to heterogeneous, user-specific task preferences), efficiency (i.e., the robot achieves sample-efficient adaptation), and scalability (i.e., the model grows sublinearly with the number of demonstrations while maintaining high performance). FLAIR surpasses benchmarks across three control tasks with an average 57% improvement in policy returns and an average 78% fewer episodes required for demonstration modeling using policy mixtures. Finally, we demonstrate the success of FLAIR in a table tennis task and find users rate FLAIR as having higher task (p<.05) and personalization (p<.05) performance.