Markov decision process
PulseAugur coverage of Markov decision process — every cluster mentioning Markov decision process across labs, papers, and developer communities, ranked by signal.
- instance of alphaXiv 90%
- instance of Gotit.pub 90%
- developed Influence Flower 90%
- instance of CatalyzeX Code Finder for Papers 90%
- instance of deep reinforcement learning 90%
- used by Deep Q-Network 90%
- used by Q-learning 90%
- used by alphaXiv 70%
- instance of ScienceCast 70%
- instance of Influence Flower 70%
- used by CatalyzeX 70%
- instance of CatalyzeX 70%
13 day(s) with sentiment data
-
LLMs enhance reinforcement learning for e-commerce fraud detection · 2 papers
Two research papers explore the use of Large Language Models (LLMs) to enhance reinforcement learning (RL) for e-commerce payment fraud detection. The first paper frames fraud detection as a multi-step Markov Decision P…
-
New framework uses LLMs and MDPs for multi-resident smart home data association
Researchers have developed a novel framework to address the data association challenge in smart homes with multiple residents. This approach models the problem as a sequential decision-making task within a Markov Decisi…
-
Reinforcement learning optimizes satellite constellation deployment
This paper proposes a reinforcement learning method to optimize the deployment of satellite constellations. The approach models the problem as a Markov Decision Process, accounting for factors like launch failures and s…
-
New 'Value Probes' method enhances AI safety auditing
Researchers have developed a new method called "Value Probes" to improve the automated red-teaming of language models. This technique frames the auditing process as a Markov decision process and utilizes beam search to …
-
New framework unifies bisimulation metrics for reinforcement learning
Researchers have developed a new framework for understanding bisimulation metrics in reinforcement learning, extending their application beyond discounted Markov decision processes (MDPs) to total- and average-reward se…
-
New Q-adaptive guidance boosts VLA model reasoning
Researchers have developed a new method called Q-adaptive guidance to improve the reasoning capabilities of vision-language-action (VLA) models. This approach treats the adjustment of reasoning weights as a Markov decis…
-
New research explores multi-agent RL, safe exploration, and efficient training methods · 10 sources tracked
Multiple research papers explore advancements in reinforcement learning (RL) and multi-agent systems. One paper introduces Octopus, a single-model framework for multi-agent RL that shares a backbone and coordinates over…
-
New method AdaRoll-GRPO optimizes LLM training with difficulty-aware rollout allocation
Researchers have developed AdaRoll-GRPO, a novel method to enhance Group Relative Policy Optimization (GRPO) training for Large Language Models (LLMs). Unlike standard GRPO which allocates a uniform rollout budget, AdaR…
-
New ML Framework Optimizes Cooperative Coevolution in Large-Scale Problems
Researchers have developed WCC, a new framework that uses machine learning to determine when to apply Cooperative Coevolution (CC) techniques in large-scale global optimization (LSGO). This approach formulates the decis…
-
New Bellman Theory Enhances Reinforcement Learning with Multi-Step Predictions
Researchers have developed a new framework for reinforcement learning that improves efficiency by incorporating multi-step transition predictions. This approach avoids exponential state-space growth by using a block-fee…
-
$M^3$ framework uses Markov Decision Process for advanced LLM jailbreaking
Researchers have developed a new framework called $M^3$ that treats multi-turn jailbreaking of large language models as a Markov Decision Process. This approach aims to improve the effectiveness of red-teaming by allowi…
-
New Optimal Control Theory for Transformer Training Unveiled
Researchers have developed a novel optimal control-theoretic framework for training Transformers. This approach models the Transformer architecture as a controlled particle system exhibiting McKean-Vlasov dynamics, whic…
-
Deep Reinforcement Learning Speeds Up Combinatorial Auctions
Researchers have developed FastCombo, a novel approach utilizing deep reinforcement learning to accelerate iterative combinatorial auctions. This method aims to reduce the costly rounds typically involved in processes l…
-
New estimator advances quantile distributional reinforcement learning accuracy
Researchers have developed a new estimator for quantile distributional reinforcement learning, aiming to accurately approximate the return distribution under a given policy. The study establishes non-asymptotic error bo…
-
New RL method enhances mission coordination in complex systems
Researchers have developed a new methodology for mission coordination in complex Systems of Systems (SoS) by integrating high-fidelity digital mission models with Reinforcement Learning (RL). This approach formulates ta…
-
New DMDP framework stabilizes state distributions in reinforcement learning
Researchers have introduced Dissimilarity-Based Markov Decision Processes (DMDPs) to stabilize state distributions in reinforcement learning. This new framework aims to ensure that state distributions converge to a desi…
-
New EPIC method enhances LLM reasoning via prefix-level policy clipping
Researchers have introduced EPIC, a novel method for improving autoregressive Large Language Model (LLM) policies using reinforcement learning. Unlike traditional token-level clipping, EPIC addresses the mismatch in pol…
-
New algorithm optimizes action masking in reinforcement learning
Researchers have developed a new algorithm for reinforcement learning that addresses the computational bottleneck of determining permissible actions. This algorithm, based on deterministic optimistic optimization, is sh…
-
AI agents to coordinate tasks via sequential auctions, replacing centralized orchestration
A new research paper proposes a decentralized framework for multi-step AI tasks using sequential auctions, moving away from traditional centralized orchestrators. This approach allows self-interested agents to bid on ta…
-
New RL method MOSE uses controlled redundancy for state construction
Researchers have developed a novel procedure for constructing provably minimal Markovian states from longitudinal causal graphs in reinforcement learning. This method, when applied to deep reinforcement learning, found …