Compute-Optimal Scaling for Value-Based Deep RL https://arxiv.org/abs/2508.14881 https://www.alphaxiv.org/ru/overview/2508.14881v1
Compute-Optimal Scaling for Value-Based Deep RL…
0 viewsОткрыть в Telegram →
Из этого канала
- #4708ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use…
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents https://arxiv.org/abs/2508.14040…
- #4709Сегодня в 22:00 мск (через час) будем презентовать нашу статью Quartet: Native…
Сегодня в 22:00 мск (через час) будем презентовать нашу статью Quartet: Native FP4 Training Can Be Optimal for Large Language Models на GPU MODE. Залетайте.
- #4710https://publish.obsidian.md/the-tensor-throne/Transformers+as+GNNs/Attention+sin…
https://publish.obsidian.md/the-tensor-throne/Transformers+as+GNNs/Attention+sinks+from+the+graph+perspective
- #4706https://jax-ml.github.io/scaling-book/gpus/
https://jax-ml.github.io/scaling-book/gpus/
- #4705OS-R1: Agentic Operating System Kernel Tuning with Reinforcement Learning…
OS-R1: Agentic Operating System Kernel Tuning with Reinforcement Learning https://arxiv.org/abs/2508.12551 https://www.alphaxiv.org/ru/overview/2508.12551v1