Performative Reinforcement Learning in Gradually Shifting Environments

2 code implementations • 15 Feb 2024 • Ben Rank, Stelios Triantafyllou, Debmalya Mandal, Goran Radanovic

This makes MDRR particularly suitable for scenarios where the environment's response strongly depends on its previous dynamics, which are common in practice.

reinforcement-learning Reinforcement Learning (RL)