Study collaborative learning among multi-agents in multi-armed bandits.
problem Minimizing group cumulative regret in a heterogeneous multi-agent setting.
method Developed decentralized algorithms for collaboration between N agents learning M stochastic multi-armed bandits. result Proved near-optimal behavior of proposed algorithms for group regret.
PCL tackles collaborative learning for diverse agents, reducing sample complexity.
problem Balancing collaborative speedup with personalization for heterogeneous agents.
method AffPCL, with bias and importance correction mechanisms.
result AffPCL reduces sample complexity by a factor of max{n−1,δ}, where n is the number of agents and δ∈[0,1] measures heterogeneity. Enhances financial analysis with multi-agent collaboration.
problem Limited use of AI-agent collaboration in financial research.
method Proposes a multi-agent system for financial investment research.
result Multi-agent system outperforms single-agent models.
Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.
problem Minimizing regret in collaborative multi-agent bandit problems.
method Proposed an algorithm with optimal regret bounds for collaborative multi-agent multi-armed bandit model.
result First algorithm with order optimal regret bounds for collaborative bandit model.
Partner-aware algorithms improve AI collaboration in multi-agent settings.
problem Improving AI cooperation in teams with shared rewards.
method Proposed Partner-Aware strategy extending Upper Confidence Bound for decentralized MAB.
result Achieves logarithmic regret in collaborative decision-making.
JPS improves joint policies for multi-agent collaboration in imperfect information games.
problem Learning good joint policies for multi-agent collaboration with imperfect information.
method Decomposes global changes to localized policy changes, iteratively improving joint policies without re-evaluating the entire game.
result JPS improves solutions provided by unilateral approaches and outperforms algorithms designed for collaborative policy learning.
New algorithm reduces regret in collaborative multi-agent bandit problems.
problem Optimizing decisions in a network of agents with communication delays.
method Follow-the-Regularized-Leader (FTRL) algorithm with suitable regularizers and communication protocols.
result Upper bound on individual regret matches lower bound up to a constant factor.
New algorithms balance collaboration and adversarial behavior in linear bandits.
problem Minimizing regret in a collaborative linear bandit problem with adversarial agents.
method Robust collaborative phased elimination algorithm with tight analyses.
result Achieves near-optimal regret bounds of $O\left(α+ 1/\sqrt{M}
ight) \sqrt{dT}$ for good agents.
New collaborative algorithm improves personalized mean estimation in online settings.
problem Online estimation of means from multiple, possibly overlapping distributions.
method Novel collaborative strategy for active querying and mean estimation.
result Algorithm improves mean estimates through communication among agents.
New algorithm reduces regret in multi-agent bandits with malicious agents.
problem Collaboration between honest and malicious agents in multi-armed bandits.
method Dynamic reduction of communication with malicious agents, learning who is malicious.
result Algorithm reduces regret even with a single malicious agent, assuming m is small compared to K. A novel method for efficient CDRL over wireless networks.
problem Challenges in collaborative deep reinforcement learning over wireless networks.
method Semantic-aware heterogeneous federated deep reinforcement learning (HFDRL) algorithm.
result Superior performance compared to state-of-the-art baselines.
A model for collaborative learning with principal-agent interaction.
problem Optimizing parameter estimates in a collaborative learning setting.
method Decision-theoretic model with aggregation coefficients and Langevin dynamics.
result Advantages in stability and generalization due to cooperative behavior.
New algorithm for collaborative bandit learning reduces sample complexity and regret.
problem Optimal arm identification in a multi-agent bandit model with communication.
method Phased elimination with data-dependent sampling schemes.
result Near-optimal algorithm for pure exploration in collaborative bandit learning.
We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key ch…
ARCO-BO optimizes multi-agent design under heterogeneity, improving efficiency and performance.
problem Heterogeneous multi-agent optimization challenges in resource use and information sharing.
method ARCO-BO integrates a consensus mechanism, budget-aware sampling, and partial input sharing for heterogeneous design spaces.
result ARCO-BO outperforms independent and collaborative BO methods in complex multi-agent settings.
TradingAgents uses LLM-powered multi-agent framework for financial trading.
problem Lack of collaborative dynamics in multi-agent financial trading systems.
method Inspired by real-world trading firms, TradingAgents features specialized LLM-powered agents and a risk management team.
result Framework outperforms baseline models in trading performance metrics.
Collab algorithm learns models from agents with missing data.
problem Learning linear models collaboratively with missing data.
method Distributed, semi-supervised algorithm with three steps: local training, aggregation, and distribution.
result Collab achieves nearly asymptotically local minimax optimal performance.
Study shows market volatility affects optimal communication design for trading strategies.
problem Investigating how communication impacts trading strategy performance in multi-agent systems.
method 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing 5 organizational structures.
result Communication improves performance but depends on market characteristics, with competitive conversation excelling in volatile tech stocks.
In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills: they must be able to encode the information received from the environment and learn how to share it with other agents as required by the task at hand. We present a deep reinforcement learn…
DiCE uses diverse agents to explore and learn, avoiding local minima.
problem Local minima in RL due to limited exploration and correlated behavior.
method DiCE employs a group of heterogeneous agents to explore simultaneously and share experiences, with a diversity regularization mechanism.
result DiCE achieves substantial improvement over baselines in MuJoCo locomotion tasks.
We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of N agents, solving the same MAB instance to minimize individual cumulative regret. In our model, agents collaborate by exchanging messages through pairwise gossip style communications on an arbitrary connected graph. We develop two no…
CollaQ improves multi-agent performance in StarCraft by 40% with fewer samples.
problem Limited generalization and high training rounds in multi-agent reinforcement learning.
method Formulates multi-agent collaboration as joint optimization on reward assignment, decomposes Q-function into self and interactive terms, and uses MARA loss.
result Improves win rate by 40% in StarCraft maps with same number of samples compared to state-of-the-art techniques.
Agents collaborate to reduce regret in a multi-agent linear bandit problem with side information.
problem Reducing regret in a multi-agent stochastic linear bandit with side information.
method A decentralized algorithm where agents communicate subspace indices and each plays a projected LinUCB on the corresponding low-dimensional subspace.
result Per-agent finite-time regret is much smaller when agents communicate compared to non-communicating case.
In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality. In this paper, we build on recent algorithmic progresses in distributed deep learning to explore various consensus-optimality trade-offs over a fixed commu…
We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their locally trained model by communicating with other agents that have similar object…
In this paper, we introduce a distributed version of the classical stochastic Multi-Arm Bandit (MAB) problem. Our setting consists of a large number of agents n that collaboratively and simultaneously solve the same instance of K armed MAB to minimize the average cumulative regret over all agents. The agents can co…
New algorithm reduces multi-agent bandit regret by sharing data.
problem Designing efficient collaboration between multi-agent linear bandits.
method Bandit Adaptive Sample Sharing (BASS) algorithm, without assumptions on bandit parameters structure.
result Validated through theoretical analysis and empirical evaluations, BASS outperforms current state-of-the-art.
Optimizes resource allocation for distributed parameter estimation in sensor networks.
problem Maximizing accuracy in parameter estimation with limited resources.
method Formulates a data collection and collaboration policy design problem as a Fisher information maximization problem. Proposes multi-armed bandit algorithms for learning the optimal policy.
result Identifies optimal data collection and collaboration policies that balance resource use and estimation accuracy.
We address challenges in collaborative black-box optimization through three frameworks.
problem Challenges in distributed experimentation, heterogeneity, and privacy in black-box optimization.
method Three unifying frameworks: global, local, and predictive.
result Shift from descriptive/predictive to prescriptive federated learning in black-box optimization.
MARLA uses deep reinforcement learning for multi-agent AHT, reducing Bayes risk.
problem Decentralized active hypothesis testing among multiple agents.
method MARLA algorithm using deep multi-agent reinforcement learning.
result MARLA outperforms single-agent learning in AHT problems.
Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous stu…
FedLCB-Q learns optimal policies from federated offline data with linear speedup.
problem Learning optimal policies from offline data with federated learning.
method Federated offline RL algorithm tailored for Q-learning, using local Q-function updates and central aggregation.
result Achieves linear speedup in sample complexity with collaboration among agents.
We consider a collaborative online learning paradigm, wherein a group of agents connected through a social network are engaged in playing a stochastic multi-armed bandit game. Each time an agent takes an action, the corresponding reward is instantaneously observed by the agent, as well as its neighbours in the social n…
Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limi…
Researchers develop multi-agent systems for quadcopters to collaborate in missions.
problem Enable multiple quadcopters to work together in remote sensing tasks.
method Agent dynamics, network topologies, collective behaviors, agreement protocol, equations of motion for quadcopters.
result Multi-agent systems can successfully collaborate in remote sensing missions.
YRC-Bench benchmarks AI agents learning to collaborate with experts.
problem Learning to recognize when to consult an expert in novel situations.
method Validation strategy and proposer-validator decomposition.
result Insights for future AI safety research.
Study designs statistical inference for collaborative science teams.
problem Maintaining scientific rigor in distributed, collaborative research.
method Analyzes hypothesis testing with strategic agents and principals.
result Principal can design policies to control posterior probability of null.
Increasing energy efficiency in buildings can reduce costs and emissions substantially. Historically, this has been treated as a local, or single-agent, optimization problem. However, many buildings utilize the same types of thermal equipment e.g. electric heaters and hot water vessels. During operation, occupants in t…
Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands fo…
This work develops a fully decentralized multi-agent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered following different behavior policies (none of which is required to explore the full state spa…
Bayesian principles improve agentic AI decision-making.
problem Decision-making under uncertainty in agentic AI systems.
method Bayesian decision theory applied to the orchestration layer of agentic AI.
result Bayesian principles enhance agentic AI's ability to make decisions under uncertainty.
The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of a remote controller. The paper investigates a distributed reinforcement learnin…
We are working to develop automated intelligent agents, which can act and react as learning machines with minimal human intervention. To accomplish this, an intelligent agent is viewed as a question-asking machine, which is designed by coupling the processes of inference and inquiry to form a model-based learning unit.…
In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) …
This work analyzes how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems.
problem Collaborative learning in distributed multi-robot systems with varying sensors and actuators.
method Simulation-based analysis using PPO and Bullet physics engine, considering different types of perturbations.
result PPO's robustness is affected by the presence of different types of perturbations and the number of agents experiencing them.
Agents collaboratively learn optimal policies in MDPs with limited capabilities.
problem Learning optimal policies in MDPs with heterogeneous agents and limited communication.
method Introduced concepts of leakage probabilities and proposed Federated-Q protocol (FedQ) for collaborative learning.
result FedQ protocol effectively aggregates knowledge and modifies learning problems for further training.
PFedRL-Rep learns shared and personalized policies for heterogeneous environments.
problem Poor performance of single policy in heterogeneous environments.
method Develops PFedRL-Rep framework with shared feature representation and personalized weights.
result Proves linear convergence speedup with respect to the number of agents.
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…