10 x 10 grid-world

The '10 x 10 grid-world' is a benchmark environment formulated as a Partially Observable Markov Decision Process (POMDP) used to evaluate reinforcement learning approaches under Metric Interval Temporal Logic (MITL) specifications.

Papers using 10 x 10 grid-world (2)

Reinforcement learning with timed constraints for robotics motion planning2026ARDNS-FN-Quantum: A Quantum-Enhanced Reinforcement Learning Framework with Cognitive-Inspired Adaptive Exploration for Dynamic Environments2025