Scaling Scaling Laws with Board Games
원문 초록
The largest experiments in machine learning now require resources far beyond the budget of all but a few institutions. Fortunately, it has recently been shown that the results of these huge experiments can often be extrapolated from the results of a sequence of far smaller, cheaper experiments. In this work, we show that not only can the extrapolation be done based on the size of the model, but on the size of the problem as well. By conducting a sequence of experiments using AlphaZero and Hex, we show that the performance achievable with a fixed amount of compute degrades predictably as the game gets larger and harder. Along with our main result, we further show that the test-time and train-time compute available to an agent can be traded off while maintaining performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Vision Language Models are Biased
4Hammer: a board-game reinforcement learning environment for the hour long time frame
Playing Non-Embedded Card-Based Games with Reinforcement Learning
ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition
Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.