openai / Vime
Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"
Stars: ✭ 310
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Vime
vehicle-trajectory-prediction
Behavior Prediction in Autonomous Driving
Stars: ✭ 23 (-92.58%)
Mutual labels: paper
Papernote
paper note, including personal comments, introduction, code etc
Stars: ✭ 268 (-13.55%)
Mutual labels: paper
Speech Separation Paper Tutorial
A must-read paper for speech separation based on neural networks
Stars: ✭ 288 (-7.1%)
Mutual labels: paper
sympy-paper
Repo for the paper "SymPy: symbolic computing in python"
Stars: ✭ 42 (-86.45%)
Mutual labels: paper
Glow
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"
Stars: ✭ 2,859 (+822.26%)
Mutual labels: paper
awesome-internals
A curated list of awesome resources and learning materials in the field of X internals
Stars: ✭ 78 (-74.84%)
Mutual labels: paper
Tucl
The first-ever paper on the Unix shell written by Ken Thompson in 1976 scanned, transcribed, and redistributed with permission
Stars: ✭ 303 (-2.26%)
Mutual labels: paper
3PU pytorch
pytorch implementation of >>Patch-base progressive 3D Point Set Upsampling<<
Stars: ✭ 61 (-80.32%)
Mutual labels: paper
Awesome-Computer-Vision-Paper-List
This repository contains all the papers accepted in top conference of computer vision, with convenience to search related papers.
Stars: ✭ 248 (-20%)
Mutual labels: paper
Purpur
Purpur is a fork of Paper, Tuinity, and Airplane with the goal of providing new and interesting configuration options, which allow for creating a unique gameplay experience not seen anywhere else
Stars: ✭ 286 (-7.74%)
Mutual labels: paper
PublicWeaklySupervised
(Machine) Learning to Do More with Less
Stars: ✭ 13 (-95.81%)
Mutual labels: paper
Awesome Ehr Deeplearning
Curated list of awesome papers for electronic health records(EHR) mining, machine learning, and deep learning.
Stars: ✭ 269 (-13.23%)
Mutual labels: paper
Surface Defect Detection
🐎📈 Constantly summarizing open source dataset and important critical papers in the field of surface defect research which are very important. 🐋
Stars: ✭ 287 (-7.42%)
Mutual labels: paper
Status: Archive (code is provided as-is, no updates expected)
How to run VIME
Variational Information Maximizing Exploration (VIME) as presented in Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks by R. Houthooft, X. Chen, Y. Duan, J. Schulman, F. De Turck, P. Abbeel (http://arxiv.org/abs/1605.09674).
To reproduce the results, you should first have rllab and Mujoco v1.31 configured. Then, run the following commands in the root folder of rllab:
git submodule add -f [email protected]:openai/vime.git sandbox/vime
touch sandbox/__init__.py
Then you can do the following:
- Execute TRPO+VIME on the hierarchical SwimmerGather environment via
python sandbox/vime/experiments/run_trpo_expl.py.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].