Q-learning
PulseAugur coverage of Q-learning — every cluster mentioning Q-learning across labs, papers, and developer communities, ranked by signal.
- instance of Markov decision processes: a tool for sequential decision making under uncertainty 90%
- instance of ScienceCast 90%
- authored by alphaXiv 70%
- used by alphaXiv 70%
- used by Markov decision processes: a tool for sequential decision making under uncertainty 70%
- instance of Gotit.pub 70%
- used by Gotit.pub 70%
- used by CatalyzeX 60%
- other ScienceCast 50%
10 day(s) with sentiment data
-
Reinforcement Learning applied to optimize cancer chemotherapy treatments
A research study has explored the application of reinforcement learning (RL) techniques for optimizing cancer chemotherapy treatments. The study focuses on generating optimal policies for sequential treatments, building…
-
Deep Double Q-learning Reduces Overestimation Bias in Reinforcement Learning
Researchers have introduced Deep Double Q-learning (DDQL), an advancement over Double DQN designed to mitigate overestimation bias in deep reinforcement learning. DDQL explicitly trains two Q-functions, unlike Double DQ…
-
New Q-learning algorithm tackles model uncertainty in decision processes
Researchers have developed a new Q-learning algorithm designed for Markov decision processes that specifically addresses model uncertainty. This algorithm operates within a finite ambiguity set, allowing for user-define…
-
AI chatbot study reveals WhatsApp's 24-hour window hinders health message delivery
A study analyzing 98,607 messages sent by an AI-powered maternal health chatbot in Nigeria revealed that WhatsApp's 24-hour customer service window significantly impacts message delivery. Messages sent outside this wind…
-
LLM agents exhibit persistent collusion even after incentives are removed
A new study published on arXiv explores the persistence of collusion among Large Language Model (LLM) agents, even after incentives for such behavior are removed or a participating agent is replaced. Researchers utilize…
-
arXiv sees new research on lifted reasoning and robust RL
Two new research papers were submitted to arXiv on October 26, 2026, focusing on distinct areas of AI. The first paper, "Query-Driven Learning for Lifted Reasoning," explores integrating learning and reasoning in first-…
-
New DRL approach integrates sentiment analysis for stock trading
A new research paper proposes a deep reinforcement learning (DRL) approach to enhance stock trading strategies by incorporating financial context and sentiment analysis. The study introduces actor-critic-based agents th…
-
Genetic programming techniques enhance MILP solvers and automate ML model assignments
Two new research papers explore the application of genetic programming techniques to enhance machine learning models. The first paper introduces Genetic Programming and Statistics-based Cut Selection (GPSCS) for Mixed-I…
-
New Q-learning method uses actions for supervision
Researchers have introduced a new approach to Q-learning called the Generative Value Classifier, which aims to improve reinforcement learning by utilizing actions as a source of supervision. Instead of solely predicting…
-
V-SHARE algorithm offers provable convergence for reinforcement learning
Researchers have introduced V-SHARE, a novel advantage-based value-learning algorithm for reinforcement learning that enhances information sharing across actions. This method decomposes the action-value function into st…
-
New framework enhances individualized treatment rules with many treatments
Researchers have developed a new framework called Neural Supervised Clustering Fusion (NSCF) to address the challenge of learning individualized treatment rules (ITRs) when dealing with a large number of potential treat…
-
New Q-learning method SGQN shows adaptive action grid benefits
Researchers have introduced Selective Growing Q-Networks (SGQN), a novel approach to Q-learning for continuous control tasks. Unlike previous methods that uniformly increase action space resolution, SGQN adaptively adds…
-
New Q-learning algorithms achieve fast rates with KL regularization
Researchers have developed new algorithms for offline Q-learning in finite-horizon Markov decision processes, incorporating Kullback-Leibler (KL) regularization. The proposed KL-regularized Q-Learning (KLQ) algorithm ac…
-
Transformers can implement Q-learning, new research shows
Researchers have theoretically demonstrated that a two-layer, attention-only Transformer can implement a form of Q-learning, a reinforcement learning algorithm. This implementation approximates greedy action selection, …
-
New Q-learning frameworks tackle reinforcement learning challenges · 4 sources tracked
Researchers have developed novel Q-learning frameworks to address challenges in reinforcement learning. One approach, Q($ ext{γ}_H$), introduces a multi-horizon Q-learning system that adaptively combines discount-specif…
-
New theoretical bounds for asynchronous Q-learning developed
Researchers have developed new theoretical bounds for asynchronous Q-learning, a reinforcement learning algorithm. The study focuses on the last iterate of Q-learning using a single trajectory from a finite Markov decis…
-
Multi-agent learning creates spatial patterns with welfare costs
A new research paper explores how spatial patterns emerge from multi-agent learning in public goods dilemmas. The study, utilizing Q-learning, found that learning rates significantly impact collective welfare, with high…
-
New Q-learning method SQAM boosts performance on complex RL tasks
Researchers have developed a new reinforcement learning technique called Q-learning with Scalar Adjoint Matching (SQAM). This method addresses challenges in fine-tuning flow policies by introducing a closed-form scalar …
-
Quantum Reinforcement Learning Slashes 5G Network Energy Use
Researchers have developed a novel Quantum Reinforcement Learning (QRL) algorithm to significantly reduce energy consumption in 5G and beyond networks. This approach addresses the challenge of high energy demand from ba…
-
New Q-learning algorithm offers model-free reachability in MDPs
Researchers have developed Quasar, a novel model-free algorithm that uses Q-learning to achieve asymptotic convergence for reachability specifications in Markov Decision Processes (MDPs) that are free of non-terminal ma…