arXiv research

A new approach for cooperative multi-agent reinforcement learning with limited communication, reducing the number of communication rounds.

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.

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.

A new MARL framework for community-based cooperation with transfer and active exploration.

Study examines Fed's pandemic communication strategies.

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.

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.

Study examines market response to concentrated policy communication using entropy measures.

Optimizes learning policies in MDPs with weakly communicating structure.

Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.

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…

Algorithm reduces long-term policy regret in ML decision-making.

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.

New algorithm reduces complexity in multi-agent reinforcement learning.

Agents learn to communicate and solve navigation tasks efficiently.

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…

A new method for MARL with partial observations reduces communication overhead.

A new parallel algorithm for learning optimal policies in MDPs with low communication costs.

MACC learns communication protocols by adapting counterfactual reasoning.

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…

SafePILCO is a Python tool for safe reinforcement learning.

New algorithm reduces individual regret and communication costs in cooperative bandits.

The paper develops algorithms to minimize queue length regret in a communication system.

AI framework for automated policy-making connects with econometrics and social choice.

I2C enables agents to learn efficient communication without redundancy.

ComEx protocol reduces communication costs in cooperative bandits.

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 …

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of …

Study improves U.S. monetary policy forecasting by integrating text and data.

Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.

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 …

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…

Agents collaboratively learn optimal policies in MDPs with limited capabilities.

DePAint solves MARL for agents with local constraints, privacy, and no central controller.

Scheduling and power allocation improve federated learning efficiency in NOMA networks.

New method reduces regret and communication costs in federated Q-learning.

A new algorithm reduces communication costs for collaborative decision-making across clients.

A framework for multi-agent communication over noisy channels in reinforcement learning.

Unified framework deciphers global central bank communications.

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.

Study Federated RL with diverse constraints, proposing new optimization methods.