Generally, Reinforcement Learning (RL) agent updates its policy by repetitively interacting with the environment, contingent on the received rewards to observed states and undertaken actions. However, the environmental disturbance, commonly leading to noisy observations (e.g., rewards and states), could significantly shape the performance of agent. Furthermore, the learning performance of Multi-Agent Reinforcement Learning (MARL) is more susceptible to noise due to the interference among intelligent agents. Therefore, it becomes imperative to revolutionize the design of MARL, so as to capably ameliorate the annoying impact of noisy rewards. In this paper, we propose a novel decomposition-based multi-agent distributional RL method by approximating the globally shared noisy reward by a Gaussian mixture model (GMM) and decomposing it into the combination of individual distributional local rewards, with which each agent can be updated locally through distributional RL. Moreover, a diffusion model (DM) is leveraged for reward generation in order to mitigate the issue of costly interaction expenditure for learning distributions. Furthermore, the optimality of the distribution decomposition is theoretically validated, while the design of loss function is carefully calibrated to avoid the decomposition ambiguity. We also verify the effectiveness of the proposed method through extensive simulation experiments with noisy rewards. Besides, different risk-sensitive policies are evaluated in order to demonstrate the superiority of distributional RL in different MARL tasks.

Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.

Governments around the world aspire to ground decision-making on evidence. Many of the foundations of policy making - e.g. sensing patterns that relate to societal needs, developing evidence-based programs, forecasting potential outcomes of policy changes, and monitoring effectiveness of policy programs - have the potential to benefit from the use of large-scale datasets or simulations together with intelligent algorithms. These could, if designed and deployed in a way that is well grounded on scientific evidence, enable a more comprehensive, faster, and rigorous approach to policy making. Integrated Assessment Models (IAM) is a broad umbrella covering scientific models that attempt to link main features of society and economy with the biosphere into one modelling framework. At present, these systems are probed by policy makers and advisory groups in a hypothesis-driven manner. In this paper, we empirically demonstrate that modern Reinforcement Learning can be used to probe IAMs and explore the space of solutions in a more principled manner. While the implication of our results are modest since the environment is simplistic, we believe that this is a stepping stone towards more ambitious use cases, which could allow for effective exploration of policies and understanding of their consequences and limitations.

Due to the agents' uniformity and quantity, their aggregate strategic choices can be approximated by the solutions of a class of ordinary differential equations. This mean-field approach has found to be an effective tool of analysis. However its current proofs rely on advanced mathematical techniques, making them less accessible. In this article, we present a simpler derivation, using only undergraduate-level probability.

We consider the problem of building an assistive robotic system that can help humans in daily household cleanup tasks. Creating such an autonomous system in real-world environments is inherently quite challenging, as a general solution may not suit the preferences of a particular customer. Moreover, such a system consists of multi-objective tasks comprising -- (i) Detection of misplaced objects and prediction of their potentially correct placements, (ii) Fine-grained manipulation for stable object grasping, and (iii) Room-to-room navigation for transferring objects in unseen environments. This work systematically tackles each component and integrates them into a complete object rearrangement pipeline. To validate our proposed system, we conduct multiple experiments on a real robotic platform involving multi-room object transfer, user preference-based placement, and complex pick-and-place tasks. Project page: https://sites.google.com/eng.ucsd.edu/home-robot

Predicting the future trajectories of dynamic agents in complex environments is crucial for a variety of applications, including autonomous driving, robotics, and human-computer interaction. It is a challenging task as the behavior of the agent is unknown and intrinsically multimodal. Our key insight is that the agents behaviors are influenced not only by their past trajectories and their interaction with their immediate environment but also largely with their long term waypoint (LTW). In this paper, we study the impact of adding a long-term goal on the performance of a trajectory prediction framework. We present an interpretable long term waypoint-driven prediction framework (WayDCM). WayDCM first predict an agent's intermediate goal (IG) by encoding his interactions with the environment as well as his LTW using a combination of a Discrete choice Model (DCM) and a Neural Network model (NN). Then, our model predicts the corresponding trajectories. This is in contrast to previous work which does not consider the ultimate intent of the agent to predict his trajectory. We evaluate and show the effectiveness of our approach on the Waymo Open dataset.

Multi-Agent Combinatorial Path Finding (MCPF) seeks collision-free paths for multiple agents from their initial to goal locations, while visiting a set of intermediate target locations in the middle of the paths. MCPF is challenging as it involves both planning collision-free paths for multiple agents and target sequencing, i.e., solving traveling salesman problems to assign targets to and find the visiting order for the agents. Recent work develops methods to address MCPF while minimizing the sum of individual arrival times at goals. Such a problem formulation may result in paths with different arrival times and lead to a long makespan, the maximum arrival time, among the agents. This paper proposes a min-max variant of MCPF, denoted as MCPF-max, that minimizes the makespan of the agents. While the existing methods (such as MS*) for MCPF can be adapted to solve MCPF-max, we further develop two new techniques based on MS* to defer the expensive target sequencing during planning to expedite the overall computation. We analyze the properties of the resulting algorithm Deferred MS* (DMS*), and test DMS* with up to 20 agents and 80 targets. We demonstrate the use of DMS* on differential-drive robots.

Conceptual and simulation models can function as useful pedagogical tools, however it is important to categorize different outcomes when evaluating them in order to more meaningfully interpret results. VERA is a ecology-based conceptual modeling software that enables users to simulate interactions between biotics and abiotics in an ecosystem, allowing users to form and then verify hypothesis through observing a time series of the species populations. In this paper, we classify this time series into common patterns found in the domain of ecological modeling through two methods, hierarchical clustering and curve fitting, illustrating a general methodology for showing content validity when combining different pedagogical tools. When applied to a diverse sample of 263 models containing 971 time series collected from three different VERA user categories: a Georgia Tech (GATECH), North Georgia Technical College (NGTC), and ``Self Directed Learners'', results showed agreement between both classification methods on 89.38\% of the sample curves in the test set. This serves as a good indication that our methodology for determining content validity was successful.

Cooperative autonomous driving plays a pivotal role in improving road capacity and safety within intelligent transportation systems, particularly through the deployment of autonomous vehicles on urban streets. By enabling vehicle-to-vehicle communication, these systems expand the vehicles environmental awareness, allowing them to detect hidden obstacles and thereby enhancing safety and reducing crash rates compared to human drivers who rely solely on visual perception. A key application of this technology is vehicle platooning, where connected vehicles drive in a coordinated formation. This paper introduces a vehicle platooning approach designed to enhance traffic flow and safety. Developed using deep reinforcement learning in the Unity 3D game engine, known for its advanced physics, this approach aims for a high-fidelity physical simulation that closely mirrors real-world conditions. The proposed platooning model focuses on scalability, decentralization, and fostering positive cooperation through the introduced predecessor-follower "sharing and caring" communication framework. The study demonstrates how these elements collectively enhance autonomous driving performance and robustness, both for individual vehicles and for the platoon as a whole, in an urban setting. This results in improved road safety and reduced traffic congestion.

Consider the classic signalling game: a sender is informed about a payoff-relevant state of the world drawn from a known distribution and takes one of several possible actions; an uninformed receiver observes the action but not the state, and makes a decision. In a landmark paper, Crawford and Sobel (1982) (henceforth CS) showed that, even if the payoff of both agents is independent of the sender's action, there are equilibria where the action transmits information about the state, as long as the conflict of interest between the agents about the ideal receiver's decision is not too large. By interpreting the payoff-irrelevant actions of the sender as "cheap talk", CS delivers a powerful formal theory of communication. Non-committal and purely symbolic behaviour can convey information and help coordinate subsequent interactions even if rational agents do not share identical goals. In this paper, we compute stationary points of independent reinforcement learning algorithms playing the CS's game of information transmission.