Picture for Philipp Moritz

Philipp Moritz

Hoplite: Efficient Collective Communication for Task-Based Distributed Systems

Add code
Feb 13, 2020
Figure 1 for Hoplite: Efficient Collective Communication for Task-Based Distributed Systems
Figure 2 for Hoplite: Efficient Collective Communication for Task-Based Distributed Systems
Figure 3 for Hoplite: Efficient Collective Communication for Task-Based Distributed Systems
Figure 4 for Hoplite: Efficient Collective Communication for Task-Based Distributed Systems
Viaarxiv icon

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

Add code
Apr 07, 2019
Figure 1 for Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
Figure 2 for Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
Figure 3 for Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
Viaarxiv icon

High-Dimensional Continuous Control Using Generalized Advantage Estimation

Add code
Oct 20, 2018
Figure 1 for High-Dimensional Continuous Control Using Generalized Advantage Estimation
Figure 2 for High-Dimensional Continuous Control Using Generalized Advantage Estimation
Figure 3 for High-Dimensional Continuous Control Using Generalized Advantage Estimation
Figure 4 for High-Dimensional Continuous Control Using Generalized Advantage Estimation
Viaarxiv icon

Ray: A Distributed Framework for Emerging AI Applications

Add code
Sep 30, 2018
Figure 1 for Ray: A Distributed Framework for Emerging AI Applications
Figure 2 for Ray: A Distributed Framework for Emerging AI Applications
Figure 3 for Ray: A Distributed Framework for Emerging AI Applications
Figure 4 for Ray: A Distributed Framework for Emerging AI Applications
Viaarxiv icon

Tune: A Research Platform for Distributed Model Selection and Training

Add code
Jul 13, 2018
Figure 1 for Tune: A Research Platform for Distributed Model Selection and Training
Figure 2 for Tune: A Research Platform for Distributed Model Selection and Training
Figure 3 for Tune: A Research Platform for Distributed Model Selection and Training
Viaarxiv icon

RLlib: Abstractions for Distributed Reinforcement Learning

Add code
Jun 29, 2018
Figure 1 for RLlib: Abstractions for Distributed Reinforcement Learning
Figure 2 for RLlib: Abstractions for Distributed Reinforcement Learning
Figure 3 for RLlib: Abstractions for Distributed Reinforcement Learning
Figure 4 for RLlib: Abstractions for Distributed Reinforcement Learning
Viaarxiv icon

Real-Time Machine Learning: The Missing Pieces

Add code
May 19, 2017
Figure 1 for Real-Time Machine Learning: The Missing Pieces
Figure 2 for Real-Time Machine Learning: The Missing Pieces
Figure 3 for Real-Time Machine Learning: The Missing Pieces
Viaarxiv icon

Trust Region Policy Optimization

Add code
Apr 20, 2017
Figure 1 for Trust Region Policy Optimization
Figure 2 for Trust Region Policy Optimization
Viaarxiv icon

A Linearly-Convergent Stochastic L-BFGS Algorithm

Add code
Apr 13, 2016
Figure 1 for A Linearly-Convergent Stochastic L-BFGS Algorithm
Figure 2 for A Linearly-Convergent Stochastic L-BFGS Algorithm
Figure 3 for A Linearly-Convergent Stochastic L-BFGS Algorithm
Viaarxiv icon

SparkNet: Training Deep Networks in Spark

Add code
Feb 28, 2016
Figure 1 for SparkNet: Training Deep Networks in Spark
Figure 2 for SparkNet: Training Deep Networks in Spark
Figure 3 for SparkNet: Training Deep Networks in Spark
Figure 4 for SparkNet: Training Deep Networks in Spark
Viaarxiv icon