3k citations · 6.2k across the 11 of their papers we have counts for
11 papers
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
Shiyi Cao, Dacheng Li, Fangzhou Zhao +12
We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integr…
Hoplite: Efficient and Fault-Tolerant Collective Communication for Task-Based Distributed Systems
Siyuan Zhuang, Zhuohan Li, Danyang Zhuo +5
Task-based distributed frameworks (e.g., Ray, Dask, Hydro) have become increasingly popular for distributed applications that contain asynchronous and dynamic workloads, including…
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…
Tune: A Research Platform for Distributed Model Selection and Training
Richard Liaw, Eric Liang, Robert Nishihara +3
Modern machine learning algorithms are increasingly computationally demanding, requiring specialized hardware and distributed computation to achieve high performance in a reasonabl…
RLlib: Abstractions for Distributed Reinforcement Learning
Eric Liang, Richard Liaw, Philipp Moritz +6
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation…
Ray: A Distributed Framework for Emerging AI Applications
Philipp Moritz, Robert Nishihara, Stephanie Wang +8
The next generation of AI applications will continuously interact with the environment and learn from these interactions. These applications impose new and demanding systems requir…
Real-Time Machine Learning: The Missing Pieces
Robert Nishihara, Philipp Moritz, Stephanie Wang +7
Machine learning applications are increasingly deployed not only to serve predictions using static models, but also as tightly-integrated components of feedback loops involving dyn…
SparkNet: Training Deep Networks in Spark
Philipp Moritz, Robert Nishihara, Ion Stoica +1
Training deep networks is a time-consuming process, with networks for object recognition often requiring multiple days to train. For this reason, leveraging the resources of a clus…
A Linearly-Convergent Stochastic L-BFGS Algorithm
Philipp Moritz, Robert Nishihara, Michael I. Jordan
We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic vari…
High-Dimensional Continuous Control Using Generalized Advantage Estimation
John Schulman, Philipp Moritz, Sergey Levine +2
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear fu…
Trust Region Policy Optimization
John Schulman, Sergey Levine, Philipp Moritz +2
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we dev…