arXiv AI
Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 12
A Mathematical Theory of Pragmatic Information
The paper introduces a pragmatic information theory that unifies communication, control, and decision-making through the isoteleia mapping, which formalizes equifinality by treating distinct semantic paths that lead to the same optimal action as pragmatically equivalent. It establishes a three-tier hierarchy of syntactic, semantic, and pragmatic information, defines pragmatic entropy, mutual information, channel capacity, and rate-distortion, and proves coding theorems that generalize Shannon’s results. The authors also present pragmatic value and cost of information, a Lagrangian dual framework for cross-layer optimization, and a pragmatic efficiency bound that quantifies the maximum net utility for resource-constrained intelligent systems, extending the theory to continuous messages and dynamic settings.
arXiv AI
Sep 15
Robust and Efficient Communication for Multi-Agent Learning
arXiv:2609.15361v1 Announce Type: cross Abstract: Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messag...
arXiv AI
Sep 2
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
The paper introduces Fed‑LSVI, a federated online reinforcement learning algorithm that uses linear function approximation in episodic Markov decision processes. It achieves a regret bound of ≥O(√{Md^3H^4T}) while only exchanging compressed sufficient statistics, thereby meeting privacy constraints. The method reduces communication cost to logarithmic in the number of episodes, a marked improvement over previous approaches that required linear communication.
arXiv Machine Learning
Aug 4
Learning to Persuade Privately Informed Receivers
arXiv:2607. 28342v1 Announce Type: cross Abstract: Bayesian persuasion studies how an informed sender can influence the behavior of a receiver through strategic information disclosure.
arXiv Machine Learning
Jul 14
Randomized Confidence Bounds for Stochastic Partial Monitoring
arXiv:2402. 05002v3 Announce Type: replace Abstract: The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback.
arXiv AI
Sep 3
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
The paper introduces a game-theoretic framework for coordinating multi-agent large language model (LLM) systems, modeling orchestrator–worker interactions as a bilevel coordination game. It analyzes textual reflection as stochastic movement over semantic memory states, providing finite-time bounds, lower bounds, and an information-theoretic impossibility result. Building on these insights, the authors propose Stochastic Reflective Memory Ascent (SRMA), a grounded evaluation mechanism that guarantees convergence under certain conditions and demonstrates improved performance on 500 SWE‑bench instances.