A new approach for cooperative multi-agent reinforcement learning with limited communication, reducing the number of communication rounds.
problem Limited communication in decentralized MARL systems leads to outdated information and unstable learning.
method Base policy prediction technique to estimate gradients and collect samples for a sequence of base policies.
result The proposed algorithm converges to an ε-Nash equilibrium with significantly fewer communication rounds and samples.
This paper proposes a novel policy for a group of agents to, individually as well as collectively, solve a multi armed bandit (MAB) problem. The policy relies solely on the information that an agent has obtained through sampling of the options on its own and through communication with neighbors. The option selection po…
A decentralized policy achieves logarithmic regret for multi-agent MAB problems with communication constraints.
problem Decentralized policy for multi-agent MAB problems with option availability and communication constraints.
method Upper Confidence Bound (UCB) algorithms with non-stationary stochastic communication protocol.
result Guaranteed logarithmic regret for non-fully connected spatial graphs with communication constraints.
This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered: multi-agent reinforcement learning (RL) and parallel RL, where frequent information exchan…
New approach uses SPG for semantic communication without a known channel model.
problem Designing efficient semantic communication systems without a known channel model.
method Applying Stochastic Policy Gradient (SPG) for reinforcement learning.
result Achieves comparable performance to model-aware approaches with a decreased convergence rate.
A new MARL framework for community-based cooperation with transfer and active exploration.
problem Flexible coordination patterns in multi-agent systems with community structures.
method Community-based multi-agent reinforcement learning with transfer and active exploration.
result Provably convergent actor-critic algorithms for structured information sharing and transfer learning.
Study examines Fed's pandemic communication strategies.
problem Analyzing Federal Reserve's communication during the COVID-19 pandemic.
method Sentiment analysis, topic modeling, comparative analysis of previous crises.
result Fed's communication during the pandemic focused on financial stability, market volatility, social welfare, and unconventional monetary policy.
Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…
Research shows SBP's tone impacts stock market returns positively or negatively.
problem Impact of State Bank of Pakistan's monetary policy communications on stock market.
method Sentiment analysis and high frequency stock market returns analysis.
result Positive or negative tone in SBP communications affects stock returns positively or negatively.
Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are al…
New RL algorithms reduce costs for single-agent and federated learning.
problem Minimizing costs in RL and federated RL settings.
method Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost algorithms.
result First algorithms to achieve low burn-in and logarithmic switching costs.
Study examines market response to concentrated policy communication using entropy measures.
problem Characterizing market response under concentrated policy communication.
method Jointly examines dispersion and information complexity (entropy) using sliding window cumulative entropy.
result Entropy captures both market volatility and narrative constraints, signaling coherent policy-driven moves.
Optimizes learning policies in MDPs with weakly communicating structure.
problem Learning optimal policies in weakly communicating MDPs with generative model.
method Span-based approach, reducing to discounted MDPs for analysis.
result First minimax optimal sample complexity bound for weakly communicating MDPs.
Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.
problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.
Encouraging sustainable mobility patterns is at the forefront of policymaking at all scales of governance as the collective consciousness surrounding climate change continues to expand. Not every community, however, possesses the necessary economic or socio-cultural capital to encourage modal shifts away from private m…
A deep RL approach learns multi-agent coordination through dynamic graph communication.
problem Learning collaborative policies in multi-agent systems.
method Connectivity Driven Communication (CDC) approach using graph-based attention mechanisms.
result CDC learns effective collaborative policies and outperforms other methods in cooperative navigation tasks.
Algorithm reduces long-term policy regret in ML decision-making.
problem Capturing long-term impacts of ML decisions in communities.
method Modeling communities as arms in a multi-armed bandit problem, defining policy regret as a stronger metric than external regret.
result Algorithm achieves provably sub-linear policy regret for long time horizons.
Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced with tasks requiring coordination and synchronisation skills, inter-agent communic…
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-…
Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.
problem Near-optimal federated Q-learning with low communication cost.
method Reference-advantage decomposition for variance reduction, synchronization between agents and server, policy update.
result Achieves almost optimal regret and near-linear regret speedup compared to single-agent learning.
New algorithm reduces complexity in multi-agent reinforcement learning.
problem High computational complexity in exact computations for multi-agent reinforcement learning.
method Design of a scalable algorithm based on Natural Policy Gradient, using local information and limited communication.
result Converges to globally optimal policy with dimension-free complexity and localization error.
Agents learn to communicate and solve navigation tasks efficiently.
problem Understanding and developing communication in artificial agents.
method Multi-agent navigation tasks in gridworld environments.
result Agents develop an interpretable communication protocol that optimally solves tasks.
A new method for MARL with partial observations reduces communication overhead.
problem Inefficient MARL algorithms in large-scale problems due to state and action information sharing.
method Distributed zeroth-order policy optimization with local policy gradient estimation using consensus.
result The method converges to a policy that is a stationary point of the global objective function.
A new parallel algorithm for learning optimal policies in MDPs with low communication costs.
problem Learning optimal policies for infinite-horizon MDPs.
method Primal-Dual Stochastic Mirror Descent for convex programming problems with inexact constraints.
result First parallel algorithm for average-reward MDPs with generative model and low communication costs.
MACC learns communication protocols by adapting counterfactual reasoning.
problem Credit assignment and non-stationarity in communication environments.
method Adapts counterfactual reasoning to overcome credit assignment and uses action policy and Q-function of other agents to handle non-stationarity.
result MACC outperforms state-of-the-art baselines in four scenarios.
While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This leads to defining weakly-communicating or multi-chain MDPs. In this…
Study of active learning in geometric block model for community detection.
problem Active learning for community detection in geometric block model.
method Proposed two active learning algorithms combining motif-counting with label query policies.
result Sampling labels of a vanishingly small fraction of nodes is sufficient for exact recovery.
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
New algorithm reduces individual regret and communication costs in cooperative bandits.
problem Optimal individual and group regret in cooperative multi-agent bandits.
method Integrates a new communication policy into a learning algorithm.
result Achieves optimal individual regret and constant communication costs.
The paper develops algorithms to minimize queue length regret in a communication system.
problem Minimizing the difference between actual and optimal queue lengths over time slots.
method Introduces queue length regret and applies algorithms from stochastic multi-armed bandit problem to analyze system performance.
result Order optimal O(1) queue length regret can be achieved with queue-length based policies. AI framework for automated policy-making connects with econometrics and social choice.
problem Improving government and economic policy-making through AI.
method Social Environment Design framework integrating Reinforcement Learning, EconCS, and Computational Social Choice.
result Promotes ethical and responsible decision making by solving open problems.
I2C enables agents to learn efficient communication without redundancy.
problem Redundant broadcast communication in multi-agent cooperation.
method I2C learns a prior for agent-agent communication via causal inference and reinforcement learning.
result I2C reduces communication overhead and improves multi-agent cooperative performance.
ComEx protocol reduces communication costs in cooperative bandits.
problem Minimizing communication costs in cooperative bandits while maintaining optimal performance.
method Developed ComEx protocol to reduce communication from Θ(T) to O(logT) messages. result Achieves state-of-the-art performance with significantly reduced communication cost.
Advances in renewable energy generation and introduction of the government targets to improve energy efficiency gave rise to a concept of a Zero Energy Building (ZEB). A ZEB is a building whose net energy usage over a year is zero, i.e., its energy use is not larger than its overall renewables generation. A collection …
This review explores how multiple agents learn to communicate in complex environments.
problem Learning effective communication strategies among multiple agents in partially observable environments.
method Review of recent algorithms and models for improving communication between agents, including Deep Recurrent Q-Networks.
result Introduction of a novel entropy-based evaluation metric for communication strategies.
Study improves U.S. monetary policy forecasting by integrating text and data.
problem Forecasting central bank policy decisions, especially the Fed's rate changes.
method Multi-modal approach combining structured data and unstructured text from Fed communications.
result Hybrid models outperform unimodal baselines, achieving a test AUC of 0.83.
Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.
problem Analyzing soft-max and policy gradient methods in bandit problems.
method Lyapunov function argument for soft-max and differential equations for policy gradient algorithms.
result Regret bounds for soft-max and a different policy gradient algorithm in bandit problems.
We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from its local task only, but it aims to learn a policy that performs well on average …
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.
How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication a…
DePAint solves MARL for agents with local constraints, privacy, and no central controller.
problem Training multi-agent systems to optimize rewards while adhering to safety constraints in a decentralized setting.
method Formulated as a decentralized constrained multi-agent Markov Decision Problem, proposed DePAint method using momentum-based decentralized policy gradient.
result First privacy-preserving fully decentralized MARL algorithm considering both peak and average constraints.
Scheduling and power allocation improve federated learning efficiency in NOMA networks.
problem Efficiently scheduling and allocating power for federated learning in bandwidth-limited wireless networks.
method Proposed a scheduling policy and power allocation scheme using NOMA to maximize data rate and convergence speed.
result Simulation results show improved federated learning accuracy in NOMA networks.
New method reduces regret and communication costs in federated Q-learning.
problem Worst-case regret and communication cost bounds in federated Q-learning.
method Gap-dependent analysis leveraging MDP structures.
result Achieves logT-type regret and communication cost bounds. A new algorithm reduces communication costs for collaborative decision-making across clients.
problem Collaborative decision-making with sparse rewards and heterogeneous contexts.
method Federated Lasso algorithm for sparse linear contextual bandits.
result Achieves near-optimal regret with logarithmic communication costs.
Unified framework deciphers global central bank communications.
problem Misinterpretations of central bank communications can disproportionately impact vulnerable populations.
method Developed the World Central Banks (WCB) dataset, annotated and reviewed sentences, defined tasks, and benchmarked models.
result A model trained on aggregated data across banks outperforms models trained on individual bank data.
A framework for multi-agent communication over noisy channels in reinforcement learning.
problem Effective communication between multiple agents in a noisy environment.
method A novel multi-agent partially observable Markov decision process (MA-POMDP) framework considering noisy communication channels.
result Jointly learned policies outperform separate learning of communication and decision making.
The implementation of optimal power flow (OPF) methods to perform voltage and power flow regulation in electric networks is generally believed to require extensive communication. We consider distribution systems with multiple controllable Distributed Energy Resources (DERs) and present a data-driven approach to learn c…
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.