drubinstein

Excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. Blog posted below

I'm very excited for @reflection_ai 's product announcement! The product team here been hard at work building the next generation of AI Agents.

Engineers spend 70% of their time understanding code, not writing it. That’s why we built Asimov at @reflection_ai. The best-in-class code research agent, built for teams and organizations.

🚀 Launch day! The NeurIPS 2025 PokéAgent Challenge is live. Two tracks: ① Showdown Battling – imperfect-info, turn-based strategy ② Pokemon Emerald Speedrunning – long horizon RPG planning 5 M labeled replays • starter kit • baselines. Bring your LLM, RL, or hybrid…

When people read ICML, do they think "I See ML; must be a computer vision conference?"

I wonder if this is how NeurIPs was coined: Neural Network Neural IPs NeurIPs? NeurIPs!

All protobufs should have field number 1 be the .proto schema. The user could use it to deserialize the received proto message.