AI trained for under $8,000 beats Stratego's top player
An MIT-CMU-NYU-Stanford team's Ataraxos AI beat Stratego's most decorated human player 15-1-4, trained for under $8,000 using decision-time search instead of massive compute.
Reinforcement learning News and Analysis
12 verified stories covering Reinforcement learning, product updates and industry developments.
Xiaomi fixes MiMo's repeated tool calls for $90,000
Xiaomi's MiMo team traced a coding-agent bug where models looped on identical tool calls back to a reinforcement-learning blind spot, and fixed it for about $90,000 instead of a $2.31 million retrain.
DeepSeek Details Sandbox System Powering 3 Million Runs a Day
DeepSeek's new paper details DSec, the sandbox system behind its agent training that launches about 3 million sandboxes a day at peak concurrency near 380,000.
Xiaomi Open-Sources MiMo-V2.6, Scores 46 on Intelligence Index
Xiaomi open-sources MiMo-V2.6, scoring 46 on Artificial Analysis's Intelligence Index after a $3.5 million, six-day reinforcement learning run.
Hugging Face Trains a Model to Paint Watercolors With 178 Images
Hugging Face detailed how GRPO reinforcement learning and a 178-image reference pool taught a coding model to paint watercolors for a few hundred dollars.
RLinf v0.3 closes the robot training loop
RLinf v0.3 turns embodied AI training into a fuller pipeline, linking data collection, SFT, reinforcement learning, evaluation and real-robot deployment.
Oak Lab sets a 20-watt goal for continuously learning agents
Oak Lab sets a 20-watt goal for continuously learning agents. The piece reviews the verified facts and why the signal matters beyond one announcement.
Richard Sutton says generative AI cannot do real science alone
The reinforcement learning pioneer argues that next-token models lack causality, experimentation and self-generated experience.
AlphaGo creator David Silver raises $1.1 billion for self-learning AI
David Silver's Ineffable Intelligence has raised $1.1 billion in a seed round at a $5.1 billion valuation, marking the largest seed round in European history. The former DeepMind researcher plans to build a "superlearner" AI through reinforcement learning, diverging from the dominant large language model approach.
Mira Murati's new company hits $12 billion valuation in 14 months
Thinking Machines Lab, founded by former OpenAI CTO Mira Murati, has secured a multibillion-dollar deal with Google Cloud for GB300 systems and reached a $12 billion valuation just 14 months after launch.
Sony's Ace table tennis robot beats humans in competitive play for the first time
Sony AI's Ace robot has defeated elite amateur and professional table tennis players in real matches, marking the first time a machine has reached elite-level performance in a competitive sport.
Kimi K1.5 validates reinforcement learning-driven reasoning
Moonshot AI's K1.5 model, released before K2, demonstrates that pure reinforcement learning can enhance reasoning capabilities, validating the approach for scaling to larger models.