Markov decision processes: a tool for sequential decision making under uncertainty
PulseAugur coverage of Markov decision processes: a tool for sequential decision making under uncertainty — every cluster mentioning Markov decision processes: a tool for sequential decision making under uncertainty across labs, papers, and developer communities, ranked by signal.
12 day(s) with sentiment data
-
AI policies learn cybersecurity penetration testing faster with history aggregation
Researchers have developed and evaluated reinforcement learning policies for penetration testing in cybersecurity scenarios with partial observability. They compared several Proximal Policy Optimization (PPO) variants, …
-
New MPC approach integrates future information for optimal decision-making
Researchers have developed a method to integrate future information into Model Predictive Control (MPC) for solving Markov Decision Processes (MDPs). This approach allows MPC, which is typically used for constraint enfo…
-
New confidence sequences improve online statistical model checking for MDPs
Researchers have developed new confidence sequences for online statistical model checking of Markov decision processes (MDPs). These sequences aim to provide more accurate and efficient guarantees when exact probabiliti…
-
New research simplifies optimal policies in Markov decision processes
Researchers have developed a new approach to understanding optimal policies in structured Markov decision processes. The study proposes boundary-based policy approximations that directly learn policy regions, contrastin…
-
New minimax PAC bounds for learning in exogenous contextual MDPs
Researchers have developed new minimax PAC bounds for learning in exogenous contextual Markov decision processes (MDPs). The study focuses on tabular discounted MDPs with exogenous, i.i.d. contexts that can influence re…
-
In-context learning may enable intrinsic curiosity in machine learning
A new research paper explores whether in-context learning (ICL) capabilities of large sequence models can support intrinsic curiosity in machine learning. The study investigates if an exploration policy can be trained t…
-
New OPE method tackles missing rewards in reinforcement learning
Researchers have developed a new method for off-policy evaluation (OPE) in reinforcement learning when rewards are missing not at random (MNAR). This approach addresses selection bias by using future states as shadow va…
-
New research explores robust optimization and reinforcement learning techniques · 6 sources tracked
Several new research papers explore advanced techniques in reinforcement learning and optimization, focusing on robustness and generative models. One paper introduces a stationary robust mean-field game framework to add…
-
In-Context Learning Explored for AI Intrinsic Curiosity
Researchers have explored whether in-context learning (ICL) capabilities of sequence models can support intrinsic curiosity in machine learning. While traditional methods for automated data selection, or "intrinsic curi…
-
AI model optimizes Type 2 Diabetes follow-up intervals, reducing costs
Researchers have developed a Contextual Markov Decision Process (CMDP) model to optimize follow-up intervals for Type 2 Diabetes (T2D) patients, moving beyond the American Diabetes Association's fixed guidelines. By ana…
-
New AI Framework Optimizes Decision-Making in Complex Environments
Researchers have developed a new method for creating performance-driven environment abstractions in large Markov decision processes. This approach focuses on optimizing decision quality by aggregating states and enforci…
-
New Q-Learning Algorithms Offer Fine-Grained Regret Bounds
Researchers have developed new algorithms for Q-learning that provide more precise regret bounds in episodic tabular Markov Decision Processes. These advancements address limitations in existing methods by offering fine…
-
ReAct Pattern Enhances LLM Reasoning and Action Capabilities
The ReAct Pattern is a design pattern for Large Language Models (LLMs) that enhances their reasoning and action capabilities in complex environments. It enables LLMs to perceive, reason, and act, allowing them to learn …
-
Lyapunov Framework Enhances Learning in Weakly-Coupled MDPs
Researchers have developed a novel Lyapunov-based framework to analyze the sample complexity of learning in weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs). This approach offers a more effic…
-
New framework simplifies DRL for complex, state-dependent actions
Researchers have introduced a new framework called Bellman-Taylor score decoding to address challenges in applying deep reinforcement learning to Markov decision processes with complex, state-dependent actions. This met…
-
New Tangle-Core Abstraction Improves Reinforcement Learning
Researchers have developed a new method for state abstraction in Markov Decision Processes called tangle-core abstraction. This approach uses graph tangles to create overlapping abstract states, which is particularly us…
-
AI research links optimal control to prospect-theory behavior
A new research paper explores how optimal control in Markov decision processes (MDPs) can inherently lead to prospect-theory-like behaviors, even without explicit utility curvature or probability weighting. The study id…
-
POMDP value functions characterized as semi-algebraic sets
Researchers have characterized the feasible set of value functions in partially observable Markov decision processes (POMDPs) as a semi-algebraic set. This extends previous work on fully observable processes, revealing …
-
New framework offers optimal sequential testing for Markovian data
Researchers have developed a new framework for sequential hypothesis testing specifically designed for data generated by Markov chains. This framework establishes a non-asymptotic lower bound on the expected stopping ti…
-
Semantic Segmentation Enhances RL Agents in 3D ViZDoom Environments
Researchers have developed new input representations for reinforcement learning agents operating in 3D environments, specifically within the ViZDoom game. By employing semantic segmentation on RGB images, the proposed m…