TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow

2017-09-08 · Danijar Hafner, James Davidson, Vincent Vanhoucke

We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in parallel, and group them to perform the neural network computation on a batch rather than individual observations. This allows the TensorFlow execution engine to parallelize computation, without the need for manual synchronization. Environments are stepped in separate Python processes to progress them in parallel without interference of the global interpreter lock. As part of this project, we introduce BatchPPO, an efficient implementation of the proximal policy optimization algorithm. By open sourcing TensorFlow Agents, we hope to provide a flexible starting point for future projects that accelerates future research in the field.

📄 PDF Abstract BibTeX arXiv:1709.02878

Code (2)

brain-research/batch-ppo 공식 구현 tf

vermashresth/damage-sim-tf-agents tf

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learning

2019-02-27 · Akshay Agrawal, Akshay Naresh Modi, Alexandre Passos, Allen Lavoie 외

TensorFlow Eager is a multi-stage, Python-embedded domain-specific language for hardware-accelerated machine learning, suitable for both interactive research and production. TensorFlow, which TensorFlow Eager extends, re…

BIG-bench Machine Learning

TensorFlow.js: Machine Learning for the Web and Beyond

2019-01-16 · Daniel Smilkov, Nikhil Thorat, Yannick Assogba, Ann Yuan 외

TensorFlow.js is a library for building and executing machine learning algorithms in JavaScript. TensorFlow.js models run in a web browser and in the Node.js environment. The library is part of the TensorFlow ecosystem, …

BIG-bench Machine Learning

Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm

2020-12-05 · Hongda Qiu

We develop a new framework for multi-agent collision avoidance problem. The framework combined traditional pathfinding algorithm and reinforcement learning. In our approach, the agents learn whether to be navigated or to…

Collision Avoidance Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

TensorFlow: A system for large-scale machine learning

2016-05-27 · Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen 외

TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. TensorFlow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. I…

BIG-bench Machine Learning Management

Should I use TensorFlow

2016-11-27 · Martin Schrimpf

Google's Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its …

BIG-bench Machine Learning General Classification