Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

Related tags

Deep LearningBPref
Overview

B-Pref

Official codebase for B-Pref: Benchmarking Preference-BasedReinforcement Learning contains scripts to reproduce experiments.

Install

conda env create -f conda_env.yml
pip install -e .[docs,tests,extra]
cd custom_dmcontrol
pip install -e .
cd custom_dmc2gym
pip install -e .
pip install git+https://github.com/rlworkgroup/[email protected]#egg=metaworld
pip install pybullet

Run experiments using GT rewards

SAC & SAC + unsupervised pre-training

Experiments can be reproduced with the following:

./scripts/[env_name]/run_sac.sh 
./scripts/[env_name]/run_sac_unsuper.sh

PPO & PPO + unsupervised pre-training

Experiments can be reproduced with the following:

./scripts/[env_name]/run_ppo.sh 
./scripts/[env_name]/run_ppo_unsuper.sh

Run experiments on irrational teacher

To design more realistic models of human teachers, we consider a common stochastic model and systematically manipulate its terms and operators:

teacher_beta: rationality constant of stochastic preference model (default: -1 for perfectly rational model)
teacher_gamma: discount factor to model myopic behavior (default: 1)
teacher_eps_mistake: probability of making a mistake (default: 0)
teacher_eps_skip: hyperparameters to control skip threshold (\in [0,1])
teacher_eps_equal: hyperparameters to control equal threshold (\in [0,1])

In B-Pref, we tried the following teachers:

Oracle teacher: (teacher_beta=-1, teacher_gamma=1, teacher_eps_mistake=0, teacher_eps_skip=0, teacher_eps_equal=0)

Mistake teacher: (teacher_beta=-1, teacher_gamma=1, teacher_eps_mistake=0.1, teacher_eps_skip=0, teacher_eps_equal=0)

Noisy teacher: (teacher_beta=1, teacher_gamma=1, teacher_eps_mistake=0, teacher_eps_skip=0, teacher_eps_equal=0)

Skip teacher: (teacher_beta=-1, teacher_gamma=1, teacher_eps_mistake=0, teacher_eps_skip=0.1, teacher_eps_equal=0)

Myopic teacher: (teacher_beta=-1, teacher_gamma=0.9, teacher_eps_mistake=0, teacher_eps_skip=0, teacher_eps_equal=0)

Equal teacher: (teacher_beta=-1, teacher_gamma=1, teacher_eps_mistake=0, teacher_eps_skip=0, teacher_eps_equal=0.1)

PEBBLE

Experiments can be reproduced with the following:

./scripts/[env_name]/[teacher_type]/[max_budget]/run_PEBBLE.sh [sampling_scheme: 0=uniform, 1=disagreement, 2=entropy]

PrefPPO

Experiments can be reproduced with the following:

./scripts/[env_name]/[teacher_type]/[max_budget]/run_PrefPPO.sh [sampling_scheme: 0=uniform, 1=disagreement, 2=entropy]

note: full hyper-paramters for meta-world will be updated soon!

DRIFT is a tool for Diachronic Analysis of Scientific Literature.

About DRIFT is a tool for Diachronic Analysis of Scientific Literature. The application offers user-friendly and customizable utilities for two modes:

Rajaswa Patil 108 Dec 12, 2022
Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" https://arxiv.org/abs/2201.13433

Third Time's the Charm? Image and Video Editing with StyleGAN3 Yuval Alaluf*, Or Patashnik*, Zongze Wu, Asif Zamir, Eli Shechtman, Dani Lischinski, Da

531 Dec 20, 2022
InterfaceGAN++: Exploring the limits of InterfaceGAN

InterfaceGAN++: Exploring the limits of InterfaceGAN Authors: Apavou Clément & Belkada Younes From left to right - Images generated using styleGAN and

Younes Belkada 42 Dec 23, 2022
This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

NeurIPS 2021 (Spotlight): Task-Adaptive Neural Network Search with Meta-Contrastive Learning This is an official PyTorch implementation of Task-Adapti

Wonyong Jeong 15 Nov 21, 2022
We present a framework for training multi-modal deep learning models on unlabelled video data by forcing the network to learn invariances to transformations applied to both the audio and video streams.

Multi-Modal Self-Supervision using GDT and StiCa This is an official pytorch implementation of papers: Multi-modal Self-Supervision from Generalized D

Facebook Research 42 Dec 09, 2022
An implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks in PyTorch.

Neural Attention Distillation This is an implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep

Yige-Li 84 Jan 04, 2023
This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018

Learning-to-See-in-the-Dark This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018, by Chen Chen, Qifeng Chen, Jia Xu, and Vl

5.3k Jan 01, 2023
[ACL 20] Probing Linguistic Features of Sentence-level Representations in Neural Relation Extraction

REval Table of Contents Introduction Overview Requirements Installation Probing Usage Citation License 🎓 Introduction REval is a simple framework for

13 Jan 06, 2023
Everything you need to know about NumPy( Creating Arrays, Indexing, Math,Statistics,Reshaping).

Everything you need to know about NumPy( Creating Arrays, Indexing, Math,Statistics,Reshaping).

1 Feb 14, 2022
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

GPT2-Pytorch with Text-Generator Better Language Models and Their Implications Our model, called GPT-2 (a successor to GPT), was trained simply to pre

Tae-Hwan Jung 775 Jan 08, 2023
Deeplab-resnet-101 in Pytorch with Jaccard loss

Deeplab-resnet-101 Pytorch with Lovász hinge loss Train deeplab-resnet-101 with binary Jaccard loss surrogate, the Lovász hinge, as described in http:

Maxim Berman 95 Apr 15, 2022
EfficientNetV2 implementation using PyTorch

EfficientNetV2-S implementation using PyTorch Train Steps Configure imagenet path by changing data_dir in train.py python main.py --benchmark for mode

Jahongir Yunusov 86 Dec 29, 2022
Deep learning toolbox based on PyTorch for hyperspectral data classification.

Deep learning toolbox based on PyTorch for hyperspectral data classification.

Nicolas 304 Dec 28, 2022
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

Ultralight-SimplePose Support NCNN mobile terminal deployment Based on MXNET(=1.5.1) GLUON(=0.7.0) framework Top-down strategy: The input image is t

223 Dec 27, 2022
Solving reinforcement learning tasks which require language and vision

Multimodal Reinforcement Learning JAX implementations of the following multimodal reinforcement learning approaches. Dual-coding Episodic Memory from

Henry Prior 31 Feb 26, 2022
Deep Learning for Natural Language Processing SS 2021 (TU Darmstadt)

Deep Learning for Natural Language Processing SS 2021 (TU Darmstadt) Task Training huge unsupervised deep neural networks yields to strong progress in

Oliver Hahn 1 Jan 26, 2022
Toward Multimodal Image-to-Image Translation

BicycleGAN Project Page | Paper | Video Pytorch implementation for multimodal image-to-image translation. For example, given the same night image, our

Jun-Yan Zhu 1.4k Dec 22, 2022
Implementation of Restricted Boltzmann Machine (RBM) and its variants in Tensorflow

xRBM Library Implementation of Restricted Boltzmann Machine (RBM) and its variants in Tensorflow Installation Using pip: pip install xrbm Examples Tut

Omid Alemi 55 Dec 29, 2022
sense-py-AnishaBaishya created by GitHub Classroom

Compute Statistics Here we compute statistics for a bunch of numbers. This project uses the unittest framework to test functionality. Pass the tests T

1 Oct 21, 2021
Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

Piggyback: https://arxiv.org/abs/1801.06519 Pretrained masks and backbones are available here: https://uofi.box.com/s/c5kixsvtrghu9yj51yb1oe853ltdfz4q

Arun Mallya 165 Nov 22, 2022