10 years after DQN, what are deep RL’s impacts on robotics? Which robotic problems have seen the most thrilling real-world successes thanks to DRL? Where do we still need to push the boundaries, and how?
Our latest survey explores these questions! Read on for more details. 👇
Peter Stone
786 posts
Prof. of Computer Science at UT Austin with research interests in AI, robotics, machine learning, multiagent systems; Executive Director of Sony AI, America
- I'm honored and proud to have been promoted to Chief Scientist of Sony AI, effective today. Looking forward to working with a fantastic worldwide team on several exciting and very ambitious projects!
- A super exciting accomplishment by my Sony AI team. Surely one of the most widespread commercial deployments of reinforcement learning!GT Sophy arrives in Gran Turismo 7 on PS5! We got an early look at the new AI: gtplanet.net/gran-turismo-s…
- Congratulations to (soon to be) Dr. Ishan Durugkar on the successful defense of his dissertation before an illustrious committee. He’s the 24th Ph.D. graduate from my lab and will soon be joining my team at Sony AI.
- I can’t express how proud I am of my Sony AI team and all our collaborators on this result of our work over the past 2 years. See the details on today’s issue of Nature!What is #GTSophy? 🏁 GT Sophy is an autonomous #AI agent trained utilizing a novel deep reinforcement learning platform. Our breakthrough research "Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning" was published today in @Nature. ow.ly/4RKH50HQOWt
- Congratulations to the whole Sony AI team on what is surely one of the largest ever commercial deployments of an end-to-end reinforcement learning agent! It’s great to see all the positive feedback from gamers!Introducing #GTSophy to @thegranturismo players of all levels is a significant milestone for the Sony AI team and the evolution of Gran Turismo. Watch @GTPlanet take on Gran Turismo Sophy 2.0 in #GY7. ow.ly/TTiQ50Q67fB
- It's now well-known (and not surprising) that current LLMs have trouble generating correct plans that require real-world knowledge. Here's a possible solution. I'm very excited about this line of work!Can LLMs reliably solve long-horizon planning problems? LLM+P: Empowering Large Language Models with Optimal Planning Proficiency Link: arxiv.org/abs/2304.11477 Code: github.com/Cranial-XIX/ll…
- Honored to be a part of the inaugural RLC. Looking forward to it!
- Proud that this paper was awarded the outstanding application paper at the conference!
- 'twas a beautiful day for a hike with (some of) my Learning Agents Research Group! @utlarg
- WisTex United won the RoboCup 2024 Standard Platform League "Challenge Shield" (lower division) competition. Collaboration with Josiah Hanna's lab at Wisconsin. Most exciting match was a 2nd half comeback (with some luck): youtube.com/live/rUyYoW4jc…
- Looking forward to my talk on Sunday afternoon!🚀 Sony AI will be at @RL_Conference 2024! Don't miss @PeterStone_TX's keynote on practical RL insights. 🔗 Read more: bit.ly/4dAmbpN #ReinforcementLearning #GranTurismo7
- Very excited about this work relating State Space Models (SSMs) to Online learning, and leading to a new, more efficient architecture!How to design State Space Models (SSM) from principles? We propose to view SSM's recurrence as the per-step closed-form solution to an online learning problem. To this end, we present Longhorn, a novel SSM that achieves 1.8x better sampling efficiency against Mamba.














