In cooperative bandits, a framework that captures essential features of collective sequential decision making, agents can minimize group regret, and thereby improve performance, by leveraging shared information. However, sharing information can be costly, which motivates developing policies that minimize group regret while also reducing the number of messages communicated by agents. Existing cooperative bandit algorithms obtain optimal performance when agents share information with their neighbors at \textit{every time step}, i.e., full communication. This requires $\Theta(T)$ number of messages, where $T$ is the time horizon of the decision making process. We propose \textit{ComEx}, a novel cost-effective communication protocol in which the group achieves the same order of performance as full communication while communicating only $O(\log T)$ number of messages. Our key step is developing a method to identify and only communicate the information crucial to achieving optimal performance. Further we propose novel algorithms for several benchmark cooperative bandit frameworks and show that our algorithms obtain \textit{state-of-the-art} performance while consistently incurring a significantly smaller communication cost than existing algorithms.

Multi-agent reinforcement learning has made substantial empirical progresses in solving games with a large number of players. However, theoretically, the best known sample complexity for finding a Nash equilibrium in general-sum games scales exponentially in the number of players due to the size of the joint action space, and there is a matching exponential lower bound. This paper investigates what learning goals admit better sample complexities in the setting of $m$-player general-sum Markov games with $H$ steps, $S$ states, and $A_i$ actions per player. First, we design algorithms for learning an $\epsilon$-Coarse Correlated Equilibrium (CCE) in $\widetilde{\mathcal{O}}(H^5S\max_{i\le m} A_i / \epsilon^2)$ episodes, and an $\epsilon$-Correlated Equilibrium (CE) in $\widetilde{\mathcal{O}}(H^6S\max_{i\le m} A_i^2 / \epsilon^2)$ episodes. This is the first line of results for learning CCE and CE with sample complexities polynomial in $\max_{i\le m} A_i$. Our algorithm for learning CE integrates an adversarial bandit subroutine which minimizes a weighted swap regret, along with several novel designs in the outer loop. Second, we consider the important special case of Markov Potential Games, and design an algorithm that learns an $\epsilon$-approximate Nash equilibrium within $\widetilde{\mathcal{O}}(S\sum_{i\le m} A_i / \epsilon^3)$ episodes (when only highlighting the dependence on $S$, $A_i$, and $\epsilon$), which only depends linearly in $\sum_{i\le m} A_i$ and significantly improves over the best known algorithm in the $\epsilon$ dependence. Overall, our results shed light on what equilibria or structural assumptions on the game may enable sample-efficient learning with many players.

The management of networks is automated by closed loops. Concurrent closed loops aiming for individual optimization cause conflicts which, left unresolved, leads to significant degradation in performance indicators, resulting in sub-optimal network performance. Centralized optimization avoids conflicts, but impractical in large-scale networks for time-critical applications. Distributed, pervasive intelligence is therefore envisaged in the evolution to B5G networks. In this letter, we propose a Q-Learning-based distributed architecture (QLC), addressing the conflict issue by encouraging cooperation among intelligent agents. We design a realistic B5G network slice auto-scaling model and validate the performance of QLC via simulations, justifying further research in this direction.

In many situations it is either impossible or impractical to develop and evaluate agents entirely on the target domain on which they will be deployed. This is particularly true in robotics, where doing experiments on hardware is much more arduous than in simulation. This has become arguably more so in the case of learning-based agents. To this end, considerable recent effort has been devoted to developing increasingly realistic and higher fidelity simulators. However, we lack any principled way to evaluate how good a "proxy domain" is, specifically in terms of how useful it is in helping us achieve our end objective of building an agent that performs well in the target domain. In this work, we investigate methods to address this need. We begin by clearly separating two uses of proxy domains that are often conflated: 1) their ability to be a faithful predictor of agent performance and 2) their ability to be a useful tool for learning. In this paper, we attempt to clarify the role of proxy domains and establish new proxy usefulness (PU) metrics to compare the usefulness of different proxy domains. We propose the relative predictive PU to assess the predictive ability of a proxy domain and the learning PU to quantify the usefulness of a proxy as a tool to generate learning data. Furthermore, we argue that the value of a proxy is conditioned on the task that it is being used to help solve. We demonstrate how these new metrics can be used to optimize parameters of the proxy domain for which obtaining ground truth via system identification is not trivial.

When it comes to games such as chess or Go, artificial intelligence (AI) programs have far surpassed the best players in the world. These "superhuman" AIs are unmatched competitors, but perhaps harder than competing against humans is collaborating with them. Can the same technology get along with people? In a new study, MIT Lincoln Laboratory researchers sought to find out how well humans could play the cooperative card game Hanabi with an advanced AI model trained to excel at playing with teammates it has never met before. In single-blind experiments, participants played two series of the game: one with the AI agent as their teammate, and the other with a rule-based agent, a bot manually programmed to play in a predefined way.

Scientific applications that involve simulation ensembles can be accelerated greatly by using experiment design methods to select the best simulations to perform. Methods that use machine learning (ML) to create proxy models of simulations show particular promise for guiding ensembles but are challenging to deploy because of the need to coordinate dynamic mixes of simulation and learning tasks. We present Colmena, an open-source Python framework that allows users to steer campaigns by providing just the implementations of individual tasks plus the logic used to choose which tasks to execute when. Colmena handles task dispatch, results collation, ML model invocation, and ML model (re)training, using Parsl to execute tasks on HPC systems. We describe the design of Colmena and illustrate its capabilities by applying it to electrolyte design, where it both scales to 65536 CPUs and accelerates the discovery rate for high-performance molecules by a factor of 100 over unguided searches.

Prior AI successes in complex games have largely focused on settings with at most hundreds of actions at each decision point. In contrast, Diplomacy is a game with more than 10^20 possible actions per turn. Previous attempts to address games with large branching factors, such as Diplomacy, StarCraft, and Dota, used human data to bootstrap the policy or used handcrafted reward shaping. In this paper, we describe an algorithm for action exploration and equilibrium approximation in games with combinatorial action spaces. This algorithm simultaneously performs value iteration while learning a policy proposal network. A double oracle step is used to explore additional actions to add to the policy proposals. At each state, the target state value and policy for the model training are computed via an equilibrium search procedure. Using this algorithm, we train an agent, DORA, completely from scratch for a popular two-player variant of Diplomacy and show that it achieves superhuman performance. Additionally, we extend our methods to full-scale no-press Diplomacy and for the first time train an agent from scratch with no human data. We present evidence that this agent plays a strategy that is incompatible with human-data bootstrapped agents. This presents the first strong evidence of multiple equilibria in Diplomacy and suggests that self play alone may be insufficient for achieving superhuman performance in Diplomacy.

In power systems, one wishes to regulate the aggregate demand of an ensemble of distributed energy resources (DERs), such as controllable loads and battery energy storage systems. We suggest a notion of predictability and fairness, which suggests that the long-term averages of prices or incentives offered should be independent of the initial states of the operators of the DER, the aggregator, and the power grid. We show that this notion cannot be guaranteed with many traditional controllers used by the load aggregator, including the usual proportional-integral (PI) controller. We show that even considering the non-linearity of the alternating-current model, this notion of predictability and fairness can be guaranteed for incrementally input-to-state stable (iISS) controllers, under mild assumptions.

Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning (MARL) settings, policy optimisation with safety awareness is particularly challenging because each individual agent has to not only meet its own safety constraints, but also consider those of others so that their joint behaviour can be guaranteed safe. Despite its importance, the problem of safe multi-agent learning has not been rigorously studied; very few solutions have been proposed, nor a sharable testing environment or benchmarks. To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods. Our solutions -- Multi-Agent Constrained Policy Optimisation (MACPO) and MAPPO-Lagrangian -- leverage the theories from both constrained policy optimisation and multi-agent trust region learning. Crucially, our methods enjoy theoretical guarantees of both monotonic improvement in reward and satisfaction of safety constraints at every iteration. To examine the effectiveness of our methods, we develop the benchmark suite of Safe Multi-Agent MuJoCo that involves a variety of MARL baselines. Experimental results justify that MACPO/MAPPO-Lagrangian can consistently satisfy safety constraints, meanwhile achieving comparable performance to strong baselines.

When it comes to games such as chess or Go, artificial intelligence (AI) programs have far surpassed the best players in the world. These "superhuman" AIs are unmatched competitors, but perhaps harder than competing against humans is collaborating with them. Can the same technology get along with people? In a new study, MIT Lincoln Laboratory researchers sought to find out how well humans could play the cooperative card game Hanabi with an advanced AI model trained to excel at playing with teammates it had never met before. In single-blind experiments, participants played two series of the game: One with the AI agent as their teammate, and the other with a rule-based agent, a bot manually programmed to play in a predefined way.