Multi-agent systems require effective coordination between groups and individuals to achieve common goals. However, current multi-agent reinforcement learning (MARL) methods primarily focus on improving individual policies and do not adequately address group-level policies, which leads to weak cooperation. To address this issue, we propose a novel Consensus-oriented Strategy (CoS) that emphasizes group and individual policies simultaneously. Specifically, CoS comprises two main components: (a) the vector quantized group consensus module, which extracts discrete latent embeddings that represent the stable and discriminative group consensus, and (b) the group consensus-oriented strategy, which integrates the group policy using a hypernet and the individual policies using the group consensus, thereby promoting coordination at both the group and individual levels. Through empirical experiments on cooperative navigation tasks with both discrete and continuous spaces, as well as Google research football, we demonstrate that CoS outperforms state-of-the-art MARL algorithms and achieves better collaboration, thus providing a promising solution for achieving effective coordination in multi-agent systems.

The famous aphorism of George Box states: "all models are wrong, but some are useful" [1]. It is the task of statisticians and data analysts to find a model which is most useful for a given problem. The build, compute, critique and repeat cycle [2], also known as Box's loop [3], is an iterative approach for finding the most useful model. Any efforts in shortening this design cycle increase the chances of developing more useful models, which in turn might yield more reliable predictions, more profitable returns or more efficient operations for the problem at hand. In this paper we choose to adopt the Bayesian formalism and therefore we will specify all tasks in Box's loop as principled probabilistic inference tasks. In addition to the well-known parameter and state inference tasks, the critique step in the design cycle is also phrased as an inference task, known as Bayesian model comparison, which automatically embodies Occam's razor [4, Ch. 28.1]. Opposed to just selecting a single model in the critique step, for different models we better quantify our confidence about which model is best, especially when data is limited [5, Ch. 18.5.1]. The uncertainty arising from prior beliefs p(m) over a set of models m and limited observations can be naturally included through the use of Bayes' theorem

Despite the subject of non-stationary bandit learning having attracted much recent attention, we have yet to identify a formal definition of non-stationarity that can consistently distinguish non-stationary bandits from stationary ones. Prior work has characterized non-stationary bandits as bandits for which the reward distribution changes over time. We demonstrate that this definition can ambiguously classify the same bandit as both stationary and non-stationary; this ambiguity arises in the existing definition's dependence on the latent sequence of reward distributions. Moreover, the definition has given rise to two widely used notions of regret: the dynamic regret and the weak regret. These notions are not indicative of qualitative agent performance in some bandits. Additionally, this definition of non-stationary bandits has led to the design of agents that explore excessively. We introduce a formal definition of non-stationary bandits that resolves these issues. Our new definition provides a unified approach, applicable seamlessly to both Bayesian and frequentist formulations of bandits. Furthermore, our definition ensures consistent classification of two bandits offering agents indistinguishable experiences, categorizing them as either both stationary or both non-stationary. This advancement provides a more robust framework for non-stationary bandit learning.

This paper proposes a novel framework for certifying the fairness of predictive models trained on biased data. It draws from query answering for incomplete and inconsistent databases to formulate the problem of consistent range approximation (CRA) of fairness queries for a predictive model on a target population. The framework employs background knowledge of the data collection process and biased data, working with or without limited statistics about the target population, to compute a range of answers for fairness queries. Using CRA, the framework builds predictive models that are certifiably fair on the target population, regardless of the availability of external data during training. The framework's efficacy is demonstrated through evaluations on real data, showing substantial improvement over existing state-of-the-art methods.

This paper investigates the problem of efficient constrained global optimization of hybrid models that are a composition of a known white-box function and an expensive multi-output black-box function subject to noisy observations, which often arises in real-world science and engineering applications. We propose a novel method, Constrained Upper Quantile Bound (CUQB), to solve such problems that directly exploits the composite structure of the objective and constraint functions that we show leads substantially improved sampling efficiency. CUQB is a conceptually simple, deterministic approach that avoid constraint approximations used by previous methods. Although the CUQB acquisition function is not available in closed form, we propose a novel differentiable sample average approximation that enables it to be efficiently maximized. We further derive bounds on the cumulative regret and constraint violation under a non-parametric Bayesian representation of the black-box function. Since these bounds depend sublinearly on the number of iterations under some regularity assumptions, we establis bounds on the convergence rate to the optimal solution of the original constrained problem. In contrast to most existing methods, CUQB further incorporates a simple infeasibility detection scheme, which we prove triggers in a finite number of iterations when the original problem is infeasible (with high probability given the Bayesian model). Numerical experiments on several test problems, including environmental model calibration and real-time optimization of a reactor system, show that CUQB significantly outperforms traditional Bayesian optimization in both constrained and unconstrained cases. Furthermore, compared to other state-of-the-art methods that exploit composite structure, CUQB achieves competitive empirical performance while also providing substantially improved theoretical guarantees.

Automatic vertebra localization and identification in CT scans is important for numerous clinical applications. Much progress has been made on this topic, but it mostly targets positional localization of vertebrae, ignoring their orientation. Additionally, most methods employ heuristics in their pipeline that can be sensitive in real clinical images which tend to contain abnormalities. We introduce a simple pipeline that employs a standard prediction with a U-Net, followed by a single graph neural network to associate and classify vertebrae with full orientation. To test our method, we introduce a new vertebra dataset that also contains pedicle detections that are associated with vertebra bodies, creating a more challenging landmark prediction, association and classification task. Our method is able to accurately associate the correct body and pedicle landmarks, ignore false positives and classify vertebrae in a simple, fully trainable pipeline avoiding application-specific heuristics. We show our method outperforms traditional approaches such as Hungarian Matching and Hidden Markov Models. We also show competitive performance on the standard VerSe challenge body identification task.

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-inefficient and maximising the standard RL objective comes with no guarantees on worst-case performance. In this paper we propose approximate model-based shielding (AMBS), a principled look-ahead shielding algorithm for verifying the performance of learned RL policies w.r.t. a set of given safety constraints. Our algorithm differs from other shielding approaches in that it does not require prior knowledge of the safety-relevant dynamics of the system. We provide a strong theoretical justification for AMBS and demonstrate superior performance to other safety-aware approaches on a set of Atari games with state-dependent safety-labels.

--As the network scale increases, existing fully distributed solutions start to lag behind the real-world challenges such as (1) slow information propagation, (2) network communication failures, and (3) external adversarial attacks. In this paper, we focus on hierarchical system architecture and address the problem of non-Bayesian learning over networks that are vulnerable to communication failures and adversarial attacks. On network communication, we consider packet-dropping link failures. We first propose a hierarchical robust push-sum algorithm that can achieve average consensus despite frequent packet-dropping link failures. We provide a sparse information fusion rule between the parameter server and arbitrarily selected network representatives. Then, interleaving the consensus update step with a dual averaging update with Kullback-Leibler (KL) divergence as the proximal function, we obtain a packet-dropping fault-tolerant non-Bayesian learning algorithm with provable convergence guarantees. On external adversarial attacks, we consider Byzantine attacks in which the compromised agents can send maliciously calibrated messages to others (including both the agents and the parameter server). T o avoid the curse of dimensionality of Byzantine consensus, we solve the non-Bayesian learning problem via running multiple dynamics, each of which only involves Byzantine consensus with scalar inputs. T o facilitate resilient information propagation across sub-networks, we use a novel Byzantine-resilient gossiping-type rule at the parameter server . As the scale of the multi-agent network increases, existing fully distributed solutions start to lag behind the crucial real-world challenges such as (1) slow information propagation, (2) network communication failures, and (3) external adversarial attacks.

AB testing aids business operators with their decision making, and is considered the gold standard method for learning from data to improve digital user experiences. However, there is usually a gap between the requirements of practitioners, and the constraints imposed by the statistical hypothesis testing methodologies commonly used for analysis of AB tests. These include the lack of statistical power in multivariate designs with many factors, correlations between these factors, the need of sequential testing for early stopping, and the inability to pool knowledge from past tests. Here, we propose a solution that applies hierarchical Bayesian estimation to address the above limitations. In comparison to current sequential AB testing methodology, we increase statistical power by exploiting correlations between factors, enabling sequential testing and progressive early stopping, without incurring excessive false positive risk. We also demonstrate how this methodology can be extended to enable the extraction of composite global learnings from past AB tests, to accelerate future tests. We underpin our work with a solid theoretical framework that articulates the value of hierarchical estimation. We demonstrate its utility using both numerical simulations and a large set of real-world AB tests. Together, these results highlight the practical value of our approach for statistical inference in the technology industry.

Robots operating in real-world environments must reason about possible outcomes of stochastic actions and make decisions based on partial observations of the true world state. A major challenge for making accurate and robust action predictions is the problem of confounding, which if left untreated can lead to prediction errors. The partially observable Markov decision process (POMDP) is a widely-used framework to model these stochastic and partially-observable decision-making problems. However, due to a lack of explicit causal semantics, POMDP planning methods are prone to confounding bias and thus in the presence of unobserved confounders may produce underperforming policies. This paper presents a novel causally-informed extension of "anytime regularized determinized sparse partially observable tree" (AR-DESPOT), a modern anytime online POMDP planner, using causal modelling and inference to eliminate errors caused by unmeasured confounder variables. We further propose a method to learn offline the partial parameterisation of the causal model for planning, from ground truth model data. We evaluate our methods on a toy problem with an unobserved confounder and show that the learned causal model is highly accurate, while our planning method is more robust to confounding and produces overall higher performing policies than AR-DESPOT.