activity
20162022
most citedTraining language models to follow instructions with human feedback

4.3k citations · 4.8k across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

18 papers · 1 filter

cs.LG202237 cited

Scaling Laws for Reward Model Overoptimization

Leo Gao, John Schulman, Jacob Hilton

In reinforcement learning from human feedback, it is common to optimize against a reward model trained to predict human preferences. Because the reward model is an imperfect proxy,…

cs.LG20217 cited

Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark

Sharada Mohanty, Jyotish Poonganam, Adrien Gaidon +20

The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning…

cs.LG2020150 cited

Scaling Laws for Autoregressive Generative Modeling

Tom Henighan, Jared Kaplan, Mor Katz +16

We identify empirical scaling laws for the cross-entropy loss in four domains: generative image modeling, video modeling, multimodal imagetext models, and mathemat…

cs.LG202049 cited

Phasic Policy Gradient

Karl Cobbe, Jacob Hilton, Oleg Klimov +1

We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework which modifies traditional on-policy actor-critic methods by separating policy and value function trai…

cs.LG2019

Leveraging Procedural Generation to Benchmark Reinforcement Learning

Karl Cobbe, Christopher Hesse, Jacob Hilton +1

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learnin…

cs.LG201918 cited

Policy Gradient Search: Online Planning and Expert Iteration without Search Trees

Thomas Anthony, Robert Nishihara, Philipp Moritz +2

Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising…