Researchers propose CURB, a reward-shaping framework to mitigate retaliatory algorithmic collusion in reinforcement learning agents. CURB detects and penalizes collusion by measuring the total variation distance between an agent's action distributions across cooperation and defection histories. This approach is guaranteed to convert any collusive fixed point into a trivial one, preventing sustained collusive equilibria.

Researchers have developed a new SAT-based framework for solving the Minimum Span Antibandwidth and Cyclic Antibandwidth Labeling problems, which are NP-hard graph labeling problems. The framework formulates the problems as decision problems and uses monotonicity to accelerate the search process. The results show that SAT-based approaches are highly competitive in solution quality.

A new algorithm, SSLD, improves DSATUR, a heuristic for the Graph Coloring Problem, by preprocessing a first good color class. This is relevant to AI agents because it may lead to future improvements in graph coloring algorithms used in AI applications.

LP-BTS is a learning-guided planning architecture for large dynamic action spaces, specifically designed for one-to-many mobile charging scenarios. It uses a graph proposal policy, a learned value critic, and edge-budgeted PUCT to evaluate and select actions. The architecture achieves state-of-the-art results in a controlled setting, outperforming various baselines and providing evidence for the effectiveness of learning-guided planning in complex action spaces.