6 papers · 1 filter
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Zhoujun Cheng, Yutao Xie, Yuxiao Qu +12
While scaling laws guide compute allocation for LLM pre-training, analogous prescriptions for reinforcement learning (RL) post-training of large language models (LLMs) remain poorl…
Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization
Matthew Landers, Taylor W. Killian, Thomas Hartvigsen +1
Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form cohe…
SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces
Matthew Landers, Taylor W. Killian, Thomas Hartvigsen +1
The combinatorial structure of many real-world action spaces leads to exponential growth in the number of possible actions, limiting the effectiveness of conventional reinforcement…
Robust Autonomy Emerges from Self-Play
Marco Cusumano-Towner, David Hafner, Alex Hertzberg +9
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust an…
Identifying Differential Patient Care Through Inverse Intent Inference
Hyewon Jeong, Siddharth Nayak, Taylor Killian +1
Sepsis is a life-threatening condition defined by end-organ dysfunction due to a dysregulated host response to infection. Although the Surviving Sepsis Campaign has launched and ha…
BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
Matthew Landers, Taylor W. Killian, Hugo Barnes +2
Offline reinforcement learning in high-dimensional, discrete action spaces is challenging due to the exponential scaling of the joint action space with the number of sub-actions an…