Results 101 to 110 of about 171,155 (269)
AGT: Efficient Offline Reinforcement Learning With Advantage‐Guided Transformer
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Offline reinforcement learning (RL) is a paradigm that seeks to train policies directly based on fixed datasets derived from previous interactions with the environment. However, offline RL faces critical challenges in environments characterised by sparse rewards and datasets dominated by suboptimal trajectories.
Jiaye Wei +4 more
wiley +1 more source
TNCOA: Efficient Exploration via Observation‐Action Constraint on Trajectory‐Based Intrinsic Reward
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Efficient exploration is critical in handling sparse rewards and partial observability in deep reinforcement learning. However, most existing intrinsic reward methods based on novelty rely on single‐step observations or Euclidean distances.
Jingxiang Ma, Hongbin Ma, Youzhi Zhang
wiley +1 more source
RAGLRO: Retrieval‐Augmented Generation With Large Language Models for Robotic Operations
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT To enable autonomous operations in complex industrial environments, this paper proposes retrieval‐augmented generation with large language models for robotic operations (RAGLRO), a robotic framework specifically designed for power switchgear operation tasks.
Wenrui Wang +6 more
wiley +1 more source
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Intrinsic motivation serves as the predominant paradigm of exploration in reinforcement learning. In pursuit of an informative and robust state representation, the behavioural metric groups behaviourally equivalent states together, which share the same single‐step reward and transition distribution.
Anjie Zhu +3 more
wiley +1 more source
MathematicsThis article presents an interpretable framework for customer segmentation and churn risk detection, integrating fuzzy clustering, explainable AI (XAI), and strategic scoring.
Gabriel Marín Díaz
doaj +1 more source
Exploring oxide quasicrystals in internal space
Acta Crystallographica Section A, EarlyView.The internal space expansion with variable system size is investigated for three different oxide quasicrystal systems. Patches of 7800, 4800 and 3600 vertices are examined in Ba–Ti–O/Pt(111), Eu–Ti–O/Pd(111) and Sr–Ti–O/Pd(111), respectively. This internal space inspection provides unique structural information for quasicrystalline systems, which goes ...
Sebastian Schenk +3 more
wiley +1 more source
The dynamics of criminal collaboration: Multiplex ties in mafia networks
Criminology, EarlyView.Abstract This study examines how social embeddedness and multiplex relationships shape criminal collaboration within organized crime networks. Drawing on data from three major investigations into the ‘Ndrangheta, we analyze how kinship, clan affiliation, leadership, and prior interactions influence participation in meetings and phone calls.
Francesco Calderoni +2 more
wiley +1 more source
Dynamic Pricing With Recommendation and Consumer Feedback
The RAND Journal of Economics, EarlyView.ABSTRACT A long‐lived seller sells a new product of unknown value by offering prices and recommendations to short‐lived consumers in continuous time. The seller receives consumer feedback about the product at a rate that increases with the instantaneous sales volume.
Wenji Xu, Shuoguang Yang
wiley +1 more source
Optimal Job Design and Information Elicitation
The RAND Journal of Economics, EarlyView.ABSTRACT When managers rely on their subordinates for local information but cannot commit to how such information is used, the incentives for effort and information elicitation become intertwined. This incentive problem influences the firm's job design decision, that is, whether to assign all tasks in a job to one worker (“individual assignment”) or ...
Arijit Mukherjee +2 more
wiley +1 more source
An extension of the basic local independence model to multiple observed classifications
British Journal of Mathematical and Statistical Psychology, EarlyView.Abstract The basic local independence model (BLIM) is appropriate in situations where populations do not differ in the probabilities of the knowledge states and the probabilities of careless errors and lucky guesses of the items. In some situations, this is not the case. This work introduces the multiple observed classification local independence model
Pasquale Anselmi +8 more
wiley +1 more source