Repository navigation

feat: tie-breaking of optimal action values by random rewards [LWCGC24, Lemma 6] - #377

Merged

lmlexplore-automation[bot] merged 3 commits into

LeanMachineLearning:mainfrom

RemyDegenne:roadmap/lwcgc24-tie-breaking-worker1

Nov 14, 2026

Merged

feat: tie-breaking of optimal action values by random rewards [LWCGC24, Lemma 6]#377
lmlexplore-automation[bot] merged 3 commits into
LeanMachineLearning:mainfrom
RemyDegenne:roadmap/lwcgc24-tie-breaking-worker1

Commits on Nov 14, 2026
- feat: tie-breaking of optimal action values by random rewards [LWCGC24, Lemma 6]
  
  committed
  1006ee8
- refactor: move reward monotonicity to Simulation, add integrable_optValue
  
  RemyDegenne
  and
  web-flow
  committed
  997a9a2
- docs: restrict the uniqueness claim of the separation lemma to 0 ≤ ω
  
  RemyDegenne
  and
  web-flow
  committed
  37b1c6e