Q-function
PulseAugur coverage of Q-function — every cluster mentioning Q-function across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
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 AI method RQA promotes cooperation in multi-agent games
Researchers have developed a new method called Reciprocal Q-Augmentation (RQA) to foster cooperation in general-sum games, where agents may have conflicting interests. RQA uses a latent-variable opponent model to augmen…
-
New Q-iteration method tackles continuous-action zero-sum Markov games
Researchers have developed a new method for online fitted Q-iteration in continuous-action zero-sum Markov games. This approach utilizes convex-concave neural network function approximators to ensure a pure-strategy sad…
-
New method enhances offline reinforcement learning with decision-centered abstractions
Researchers have developed a new method for offline reinforcement learning that focuses on creating decision-centered abstractions. This approach aims to preserve crucial information for learning optimal actions while d…
-
Research questions Q-function pretraining in RL fine-tuning
A new research paper questions the necessity of pretraining Q-functions in reinforcement learning (RL) when fine-tuning a policy. The study found that naive Q-function pretraining often offers minimal advantage over ran…
-
New RL method uses K-step lookahead for faster learning
Researchers have developed a novel approach to reinforcement learning in non-episodic, finite-horizon Markov decision processes (MDPs). The method introduces a modified Q-function that limits planning to a K-step lookah…
-
New DRRL Algorithm Achieves Finite-Time Convergence with Linear Approximation
Researchers have developed a new algorithm for Distributionally Robust Reinforcement Learning (DRRL) that provides finite-time convergence guarantees even with linear function approximation. This algorithm addresses lim…
-
AI researchers develop new value functions for temporal logic policies
Researchers have developed a new method for constructing optimal policies for temporal logic specifications in reinforcement learning. This approach builds upon existing work by decomposing value functions and creating …