brain-research/mirage-rl brain-research/mirage-rl

  • This repository has been archived on 10/Nov/2022
  • Stars
    star
    17
  • Rank 1,257,181 (Top 25 %)
  • Language
    Python
  • License
    MIT License
  • Created over 6 years ago
  • Updated over 6 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
brain-research/mirage-rl
github

brain-research

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code to reproduce the experiments in The Mirage of Action-Dependent Baselines in Reinforcement Learning.

More Repositories

1

self-attention-gan

Python
976
star
2

realistic-ssl-evaluation

Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"
Python
452
star
3

guided-evolutionary-strategies

Guided Evolutionary Strategies
Jupyter Notebook
263
star
4

acai

Code for "Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer"
Python
240
star
5

mpnn

Open source implementation of "Neural Message Passing for Quantum Chemistry"
Python
220
star
6

tensorfuzz

A library for performing coverage guided fuzzing of neural networks
Python
204
star
7

nngp

Deep neural network kernel for Gaussian process
Python
194
star
8

l2hmc

TensorFlow implementation for training MCMC samplers from the paper: Generalizing Hamiltonian Monte Carlo with Neural Network
Jupyter Notebook
180
star
9

deep-molecular-massspec

Mass Spectrometry for Small Molecules using Deep Learning
Python
110
star
10

long-term-video-prediction-without-supervision

Implementation of Hierarchical Long-term Video Prediction without Supervision
Python
91
star
11

data-linter

The Data Linter identifies potential issues (lints) in your ML training data.
Python
84
star
12

conv-sv

The Singular Values of Convolutional Layers
Python
71
star
13

ncp

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors
Python
63
star
14

mean-field-cnns

Jupyter Notebook
35
star
15

LeaveNoTrace

Leave No Trace is an algorithm for safe reinforcement learning.
Python
15
star
16

fisher-rao-regularization

Python
10
star
17

wip-lambada-lm

LSTM language model on LAMBADA dataset
Python
9
star
18

hyperbolictext

TensorFlow source code for learning embeddings of text sequences in an unsupervised manner.
Python
8
star
19

wip-constrained-extractor

Work in progress inference, learning, and evaluation code for extractive summarization.
Python
6
star
20

flying-shapes

A potentially infinite dataset of coloured shapes which bounce around on a black background.
Python
4
star
21

metaq

Python
3
star