Decision Transformer: A brand new Offline RL Pattern

Overview

DecisionTransformer_StepbyStep

Intro

Decision Transformer: A brand new Offline RL Pattern.

这是关于NeurIPS 2021 热门论文Decision Transformer的复现。

👍 原文地址: Decision Transformer: Reinforcement Learning via Sequence Modeling

👍 官方的Git仓库: decision-transformer(official)

Decision Transformer

Decision Transformer属于Offline RL,所谓Offline RL,即从次优数据中学习策略来分配Agent,即从固定、有限的经验中产生最大有效的行为。

👀️ Motivation

DT将RL看成一个序列建模问题(Sequence Modeling Problem ),不用传统RL方法,而使用网络直接输出动作进行决策。传统RL方法存在一些问题,比如估计未来Return过程中Bootstrapping过程会导致Overestimate; 马尔可夫假设;

DT借助了Transformer的强大表征能力和时序建模能力。

  • Decision Transformer的表现达到甚至超过了目前最好的基于dynamic programming的主流方法;
  • 在一些需要long-term credit assignment的task【例如sparse reward或者delayed reward等】,Decision Transformer的表现远超过了最好的主流方法.

🚀️ DT的核心思想

image.png

Decision Transformer的核心思想; States、Actions、Returns被Fed into Modality-Specific的线性Embedding;并添加了带有时间步信息的positional episodic timestep; 这些Tokens被输入一个GPT架构,使用a causal self-attention mask来预测actions。

🎉️ DT的优势

  1. 无需Markov假设;
  2. 没有使用一个可学习的Value Function作为Training Target;
  3. 利用Transformer的特性,绕过长期信用分配进行“自举bootstrapping”的需要,避免了时序差分学习的“短视”行为;
  4. 可以通过self-attention直接执行信度分配。这与缓慢传播奖励并容易产生干扰信号的 Bellman Backup 相反,可以使 Transformer 在奖励稀少或分散注意力的情况下仍然有效地工作.

Dependencies

1. D4RL ( Dataset for Deep Data-Driven Reinforcement Learning )

2. MUJOCO 210

# 安装之前先安装absl-py和matplotlib 
pip install absl-py 
pip install matplotlib 

"""
git clone https://github.com/rail-berkeley/d4rl.git
cd d4rl
pip install -e . # 这种方法不好使 !! 
"""

#首先在https://github.com/deepmind/dm_control这个库git clone
# cd
pip install -r requirement.txt 
# 然后 
pip install matplotlib 
# 然后 https://github.com/takuseno/d3rlpy 
pip install d3rlpy 
# 然后安装mujoco 210  
# 直接安装,然后添加环境变量 
# 装完之后进d4rl文件夹下
python setup.py install 
# 成功安装 d4rl 1.1 

3. GPT-2


pip install transformers

Experiments

Group1: Decision Transformer — Hopper-v3-Medium-Dataset

参数Config

class Config:
    env = "hopper"
    dataset = "medium"
    mode = "normal" # "delayed" : all rewards moved to end of trajectory
    device = 'cuda'
    log_dir = 'TB_log/'
    record_algo = 'DT_Hopper_v1'
    test_cycles = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')

    # 模型
    model_type = "DT"
    activation_function = 'relu'

    # Scalar
    max_length = 20 # max_len # K
    pct_traj = 1.
    batch_size = 64
    embed_dim = 128
    n_layer = 3
    n_head = 1
    dropout = 0.1
    lr = 1e-4
    wd = 1e-4
    warmup_steps = 1000
    num_eval_episodes = 100
    max_iters = 50
    num_steps_per_iter = 1000

    # Bool
    log_to_tb = True

效果

image.png

Owner
Irving
Irving
基于Paddle框架的arcface复现

arcface-Paddle 基于Paddle框架的arcface复现 ArcFace-Paddle 本项目基于paddlepaddle框架复现ArcFace,并参加百度第三届论文复现赛,将在2021年5月15日比赛完后提供AIStudio链接~敬请期待 参考项目: InsightFace Padd

QuanHao Guo 16 Dec 15, 2022
Implementations of LSTM: A Search Space Odyssey variants and their training results on the PTB dataset.

An LSTM Odyssey Code for training variants of "LSTM: A Search Space Odyssey" on Fomoro. Check out the blog post. Training Install TensorFlow. Clone th

Fomoro AI 95 Apr 13, 2022
Fake News Detection Using Machine Learning Methods

Fake-News-Detection-Using-Machine-Learning-Methods Fake news is always a real and dangerous issue. However, with the presence and abundance of various

Achraf Safsafi 1 Jan 11, 2022
The pytorch implementation of SOKD (BMVC2021).

Semi-Online Knowledge Distillation Implementations of SOKD. Requirements This repo was tested with Python 3.8, PyTorch 1.5.1, torchvision 0.6.1, CUDA

4 Dec 19, 2021
Fluency ENhanced Sentence-bert Evaluation (FENSE), metric for audio caption evaluation. And Benchmark dataset AudioCaps-Eval, Clotho-Eval.

FENSE The metric, Fluency ENhanced Sentence-bert Evaluation (FENSE), for audio caption evaluation, proposed in the paper "Can Audio Captions Be Evalua

Zhiling Zhang 13 Dec 23, 2022
SwinIR: Image Restoration Using Swin Transformer

SwinIR: Image Restoration Using Swin Transformer This repository is the official PyTorch implementation of SwinIR: Image Restoration Using Shifted Win

Jingyun Liang 2.4k Jan 05, 2023
Adversarially Learned Inference

Adversarially Learned Inference Code for the Adversarially Learned Inference paper. Compiling the paper locally From the repo's root directory, $ cd p

Mohamed Ishmael Belghazi 308 Sep 24, 2022
An official implementation of MobileStyleGAN in PyTorch

MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis Official PyTorch Implementation The accompanying videos c

Sergei Belousov 602 Jan 07, 2023
Convert scikit-learn models to PyTorch modules

sk2torch sk2torch converts scikit-learn models into PyTorch modules that can be tuned with backpropagation and even compiled as TorchScript. Problems

Alex Nichol 101 Dec 16, 2022
AMTML-KD: Adaptive Multi-teacher Multi-level Knowledge Distillation

AMTML-KD: Adaptive Multi-teacher Multi-level Knowledge Distillation

Frank Liu 26 Oct 13, 2022
HIVE: Evaluating the Human Interpretability of Visual Explanations

HIVE: Evaluating the Human Interpretability of Visual Explanations Project Page | Paper This repo provides the code for HIVE, a human evaluation frame

Princeton Visual AI Lab 16 Dec 13, 2022
PyTorch implementation of the Flow Gaussian Mixture Model (FlowGMM) model from our paper

Flow Gaussian Mixture Model (FlowGMM) This repository contains a PyTorch implementation of the Flow Gaussian Mixture Model (FlowGMM) model from our pa

Pavel Izmailov 124 Nov 06, 2022
A bunch of random PyTorch models using PyTorch's C++ frontend

PyTorch Deep Learning Models using the C++ frontend Gettting started Clone the repo 1. https://github.com/mrdvince/pytorchcpp 2. cd fashionmnist or

Vince 0 Jul 13, 2021
“袋鼯麻麻——智能购物平台”能够精准地定位识别每一个商品

“袋鼯麻麻——智能购物平台”能够精准地定位识别每一个商品,并且能够返回完整地购物清单及顾客应付的实际商品总价格,极大地降低零售行业实际运营过程中巨大的人力成本,提升零售行业无人化、自动化、智能化水平。

thomas-yanxin 192 Jan 05, 2023
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

LoFTR: Detector-Free Local Feature Matching with Transformers Project Page | Paper LoFTR: Detector-Free Local Feature Matching with Transformers Jiami

ZJU3DV 1.4k Jan 04, 2023
Simple implementation of OpenAI CLIP model in PyTorch.

It was in January of 2021 that OpenAI announced two new models: DALL-E and CLIP, both multi-modality models connecting texts and images in some way. In this article we are going to implement CLIP mod

Moein Shariatnia 226 Jan 05, 2023
An end-to-end project on customer segmentation

End-to-end Customer Segmentation Project Note: This project is in progress. Tools Used in This Project Prefect: Orchestrate workflows hydra: Manage co

Ocelot Consulting 8 Oct 06, 2022
A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''

README.md shall be finished soon. WSSGG 0 Overview 1 Installation 1.1 Faster-RCNN 1.2 Language Parser 1.3 GloVe Embeddings 2 Settings 2.1 VG-GT-Graph

Keren Ye 35 Nov 20, 2022
Implementations of the algorithms in the paper Approximative Algorithms for Multi-Marginal Optimal Transport and Free-Support Wasserstein Barycenters

Implementations of the algorithms in the paper Approximative Algorithms for Multi-Marginal Optimal Transport and Free-Support Wasserstein Barycenters

Johannes von Lindheim 3 Oct 29, 2022
A Unified Framework and Analysis for Structured Knowledge Grounding

UnifiedSKG 📚 : Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models Code for paper UnifiedSKG: Unifying and Mu

HKU NLP Group 370 Dec 21, 2022