Unverified50% confidenceFactExact time
The DQN system was able to reach or surpass human-level performance on 49 Atari games using only raw pixel input.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDQN在Atari游戏中堆叠最近4帧画面作为输入75% similarUnverified视觉强化学习范式在Atari游戏（DQN, 2013）中获得突破性验证70% similarUnverifiedPhysical Atari has a robot observe a real game screen with a camera and operate a real controller with a robotic hand, completing games amid real latency, noise, and mechanical error.64% similarUnverifiedBilibili UP creator 大肥鱼 released a single titled 《AI末日概率上升中↑》, presented in the form of an animated PV rendered purely with code.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989577API
curl https://kongchang.com/api/v1/knowledge/claims/989577MCP
get_claim(id=989577)