Microsoft Research ブログ
読み込み中…
Microsoft Research ブログ
Three new reinforcement learning methods aim to improve AI in gaming and beyond
| Kamil Ciosek, Sam Devlin, と Katja Hofmann
Reinforcement learning (RL) provides exciting opportunities for game development, as highlighted in our recently announced Project Paidia (opens in new tab)—a research collaboration between our Game Intelligence group at Microsoft Research Cambridge and game developer Ninja Theory. In Project Paidia,…
Microsoft Research ブログ
Learning local and compositional representations for zero-shot learning
| Tristan Sylvain, Devon Hjelm, と Linda Petrini
In computer vision, one key property we expect of an intelligent artificial model, agent, or algorithm is that it should be able to correctly recognize the type, or class, of objects it encounters. This is critical in numerous important real-world…