Map of 171,250 RL papers shows deep RL and robotics dominate the field
CatAstro_Piyush · x · 2026-10-18
A comprehensive literature map covering 171,250 reinforcement learning studies (mostly 2011–2025) slices the field into 11 major clusters: deep RL and robotics (42,337 papers, the largest), RL for wireless networks (26,048), foundations of RL (20,109), neuroscience of reward-based learning (11,825), plus 19,305 ungrouped studies.
Most-cited authors inside the field include Sergey Levine (in-field h-index 51), Pieter Abbeel (44), Richard Sutton (41), David Silver (37), and Frank Lewis (37), with recent works like SkillBlender for humanoid whole-body loco-manipulation. The tool also offers curated reading entry points (Core, Rising, Experts) and a term cloud highlighting dominant vocabulary like deep reinforcement learning, policy, and reward.
More from Research
- KNOWS benchmark: best web agent fully succeeds in fewer than 3% of complex long-horizon tasks — anmarasovic · 2026-10-18
- When is Majority Vote optimal? Study precisely characterizes crowdsourced label aggregation — burkov · 2026-10-18
- Google tops US AI institutions by highly cited researchers, CMU and NVIDIA follow — NegotiationOk7535 · 2026-10-18
- Every Citation Right, Answer Still Wrong 9/9: Code-Checked Conditions Fixed RAG to 5/6 — International_Elk_33 · 2026-10-18
- KNOWS Benchmark: Best Web Agent Fully Succeeds on Fewer Than 3% of Complex Tasks — anmarasovic · 2026-10-18
- Open-source Engram memory engine, modeled on databases, matches Mem0 on BEAM — phecdaYm · 2026-10-18