资源算法NTM_RL

NTM_RL

2020-02-26 | |  35 |   0 |   0

NTM_RL

Experiments to use Neural Turing Machines in Partially observable Environments with Reinforcement Learning Algorithms

Usage

Use the test_agent.py script to start the experiment. It takes 3 parameters:

  • train/test to indicate if train or test

  • the agent

  • the environment

An example of the command is: python .test_agent.py train DQNAgent_NTM MazeExploration7x7FixedMap-v0

This project is using:


上一篇:ntm_extension

下一篇:EH_NTMap

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...