all tags

reward-shaping

3 notes carry this tag — 2 claims, 1 capture. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• CoDA couples a generative-simulation data engine and a robot policy through shared memory, compiling a vision-language critic's failure diagnoses into regeneration programs and optimality-preserving dense rewards
  claim seedling Tier 1 2026-10-19 · robotics, vision-language-action, generative-simulation, reinforcement-learning, reward-shaping
• CoDA: Co-Evolution of Data Engines and Action Policies (arXiv:2610.22362) — capture
  capture promoted Tier 1 2026-10-18 · robotics, vision-language-action, generative-simulation, reinforcement-learning, reward-shaping
• Microcosmos's evolved chemotaxis is fitness-rewarded via an explicit energy term, not spontaneously emergent
  claim seedling Tier 1 2026-08-20 · artificial-life, neuroevolution, reward-shaping, quality-diversity, microcosmos