Just about every AI advance you’ve heard of depends on a breakthrough that’s three decades old. Keeping up the pace of progress will require confronting AI’s serious limitations.
MIT and SenseTime today announced that SenseTime, a leading artificial intelligence (AI) company, is joining MIT's efforts to define the next frontier of human and machine intelligence.
A Key Challenge In Complex Visuomotor Control Is Learning Abstract Representations That Are Effective For Specifying Goals, Planning, And Generalization. To This End, We Introduce Universal Planning Networks (upn). Upns Embed Differentiable Planning Within A Goal-directed Policy. This Planning Computation Unrolls A Forward Model In A Latent Space And Infers An Optimal Action Plan Through Gradient Descent Trajectory Optimization. The Plan-by-gradient-descent Process And Its Underlying Representations Are Learned End-to-end To Directly Optimize A Supervised Imitation Learning Objective. We Find That The Representations Learned Are Not Only Effective For Goal-directed Visual Imitation Via Gradient-based Trajectory Optimization, But Can Also Provide A Metric For Specifying Goals Using Images. The Learned Representations Can Be Leveraged To Specify Distance-based Rewards To Reach New Target States For Model-free Reinforcement Learning, Resulting In Substantially More Effective Learning When Solving New Tasks Described Via Image-based Goals. We Were Able To Achieve Successful Transfer Of Visuomotor Planning Strategies Across Robots With Significantly Different Morphologies And Actuation Capabilities.
Next time you’re at King’s Cross station, take a moment to think about this. Just yards from where you’re standing, the world’s most advanced artificial intelligence (AI) technology is being developed — by a London company called DeepMind.
S. Albrecht, und P. Stone. (2017)cite arxiv:1709.08071Comment: 42 pages, submitted for review to Artificial Intelligence Journal. Keywords: multiagent systems, agent modelling, opponent modelling, survey, open problems.