AI beats us at another game: STRATEGO | DeepNash paper explained

DeepMind made an expert-level Stratego bot. We explain how they program an unexploitable AI player and we go into more details while explaining their model-free Reinforcement Learning method and how they achieve Nash Equilibrium with Regularized Nash Dynamics.
► Sponsor: NVIDIA: 👉 https://nvda.ws/3HpWbzX Sign up for the GTC spring 2023 for FREE!
Google Form to enter DLI credits giveaway: https://forms.gle/DMPc4G22tnqbMWGCA

Check out our daily #MachineLearning Quiz Questions: https://www.youtube.com/c/AICoffeeBreak/community

📜 DeepNash paper: Perolat, J., De Vylder, B., Hennes, D., Tarassov, E., …

bot deepmind dynamics equilibrium expert explained free game gtc information nash equilibrium nvidia paper reinforcement reinforcement learning support