David Silver — Pionir Reinforcement Learning

Ilmuwan komputer Inggris, peneliti utama di DeepMind. Pencetus AlphaGo (2016), AlphaZero (2017), dan kontributor utama reinforcement learning modern.

Silver: DQN (2013, dengan DeepMind), AlphaGo (2016), AlphaZero (2017), MuZero (2019), AlphaProof (2024). Profesor UCL. Pioneer RL modern.

Print

David Silver

Biodata

  • Lahir: 1976, Inggris
  • Profesi: AI researcher

Kontribusi

  • DQN (Deep Q-Network, 2013) — pertama RL yang melebihi manusia di Atari
  • AlphaGo (2016) — kalahkan Lee Sedol
  • AlphaZero (2017) — belajar dari nol, master catur/go/shogi
  • MuZero (2019) — belajar tanpa model
  • AlphaProof (2024) — silver medal IMO
  • AlphaGeometry (2024) — geometri Olympiad
  • AIXI — teori agent

Karier

  • University of Alberta (PhD)
  • UCL — Professor
  • DeepMind — Principal Research Scientist

Pandangan

  • Reward is enough (2021) — “kecerdasan, dan kemampuan yang terkait, dapat dipahami sebagai memaksimalkan reward”
  • RL adalah path paling menjanjikan ke AGI

Connected to

Not yet written

The following pages are referenced but don't exist yet — they'd make good future additions.

  • /concepts/reinforcement-learning
  • /timeline/peluncuran-alphago

References

  1. Wikipedia

Type at least 2 characters to search.

Press to navigate, to open, esc to close.