Phillip Isola highlights a non-mainstream AI route: RL from scratch via ultra-fast simulators
AjdDavison · x · 2026-09-15
MIT professor Phillip Isola recommends the research pursued by Joseph and team, who take a very different approach from the mainstream: they build extremely fast simulators and optimizers — so fast that reinforcement learning can be done from scratch even on hard domains. The results are described as "very cool," and retweeter AjdDavison flags it as worth watching.
More from Research
- Microsoft's ESRL boosts MoE RL via expert-space exploration — MicrosoftResearch · 2026-09-15
- Grouped Value Attention shrinks KV cache by reconstructing keys on demand — Vishesh Tripathi · 2026-09-15
- Amazon's MInTRL uses sparse off-policy interventions to boost on-policy RL — amazon · 2026-09-15
- Stateless LLM failover preserves ~0% context; ContinuityBench proxy hits 99.20% CPR — its_vayishu · 2026-09-15
- Cutting AI verifier reading cost: top-50 retrieval kept just 2 of 8 minority evidence items — iMiguelmars · 2026-09-15
- SSAD2026 talk covers autonomous driving 3D perception, from LiDAR self-supervision to multi-sensor distillation — abursuc · 2026-09-15