GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → Sheng-J → DOM-Q-NET

Sheng-J / DOM-Q-NET

Licence: other
Graph-based Deep Q Network for Web Navigation

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

reinforcement-learningqlearningrlgraph-based-learninggraph-neural-networksrainbow-dqndqn-pytorch

Projects that are alternatives of or similar to DOM-Q-NET

dqn zoo
The implement of all kinds of dqn reinforcement learning with Pytorch
Stars: ✭ 42 (+40%)
Mutual labels:  rainbow-dqn
AGCN
No description or website provided.
Stars: ✭ 17 (-43.33%)
Mutual labels:  graph-neural-networks
MTAG
Code for NAACL 2021 paper: MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences
Stars: ✭ 23 (-23.33%)
Mutual labels:  graph-neural-networks
SBR
⌛ Introducing Self-Attention to Target Attentive Graph Neural Networks (AISP '22)
Stars: ✭ 22 (-26.67%)
Mutual labels:  graph-neural-networks
GKT
Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network
Stars: ✭ 43 (+43.33%)
Mutual labels:  graph-based-learning
mtad-gat-pytorch
PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).
Stars: ✭ 85 (+183.33%)
Mutual labels:  graph-neural-networks
ProteinGCN
ProteinGCN: Protein model quality assessment using Graph Convolutional Networks
Stars: ✭ 88 (+193.33%)
Mutual labels:  graph-neural-networks
NMN
Source code and datasets for ACL 2020 paper: Neighborhood Matching Network for Entity Alignment.
Stars: ✭ 55 (+83.33%)
Mutual labels:  graph-neural-networks
Deep-QLearning-Demo-csharp
This demo is a C# port of ConvNetJS RLDemo (https://cs.stanford.edu/people/karpathy/convnetjs/demo/rldemo.html) by Andrej Karpathy
Stars: ✭ 34 (+13.33%)
Mutual labels:  qlearning
DIN-Group-Activity-Recognition-Benchmark
A new codebase for Group Activity Recognition. It contains codes for ICCV 2021 paper: Spatio-Temporal Dynamic Inference Network for Group Activity Recognition and some other methods.
Stars: ✭ 26 (-13.33%)
Mutual labels:  graph-neural-networks
Gradient-Samples
Samples for TensorFlow binding for .NET by Lost Tech
Stars: ✭ 53 (+76.67%)
Mutual labels:  rl
PathCon
Combining relational context and relational paths for knowledge graph completion
Stars: ✭ 94 (+213.33%)
Mutual labels:  graph-neural-networks
rl
Generic reinforcement learning codebase in TensorFlow
Stars: ✭ 88 (+193.33%)
Mutual labels:  rl
DeepBeerInventory-RL
The code for the SRDQN algorithm to train an agent for the beer game problem
Stars: ✭ 27 (-10%)
Mutual labels:  rl
reinforced-race
A model car learns driving along a track using reinforcement learning
Stars: ✭ 37 (+23.33%)
Mutual labels:  qlearning
well-classified-examples-are-underestimated
Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"
Stars: ✭ 21 (-30%)
Mutual labels:  graph-neural-networks
Reinforcement-Learning-An-Introduction
Kotlin implementation of algorithms, examples, and exercises from the Sutton and Barto: Reinforcement Learning (2nd Edition)
Stars: ✭ 28 (-6.67%)
Mutual labels:  qlearning
Reinforcement-Learning-CheatSheet
Cheatsheet of Reinforcement Learning (Based on Sutton-Barto Book - 2nd Edition)
Stars: ✭ 22 (-26.67%)
Mutual labels:  rl
PathCon
Combining relational context and relational paths for knowledge graph completion
Stars: ✭ 29 (-3.33%)
Mutual labels:  graph-neural-networks
DiGCN
Implement of DiGCN, NeurIPS-2020
Stars: ✭ 25 (-16.67%)
Mutual labels:  graph-neural-networks
View All Similar Projects ➔

DOM-Q-NET: Grounded RL on Structured Language

"DOM-Q-NET: Grounded RL on Structured Language" International Conference on Learning Representations (2019). Sheng Jia, Jamie Kiros, Jimmy Ba. [arxiv] [openreview]
Architecture

Demo

Trained multitask agent: https://www.youtube.com/watch?v=eGzTDIvX4IY
Facebook login: https://www.youtube.com/watch?v=IQytRUKmWhs&t=2s

Requirement

Need to download selenium & install chrome driver for selenium..

Installation

  1. Clone this repo
  2. Download MiniWoB++ environment from the original repo https://github.com/stanfordnlp/miniwob-plusplus
    and copy miniwob-plusplus/html folder to miniwob/html in this repo
  3. In fact, this html folder could be stored anywhere, but remember to perform one of the following actions:
  • Set environment variable "WOB_PATH" to
    file://"your-path-to-miniwob-plusplus"/html/miniwob
    E.g. "your-path-to-miniwob-plusplus" is "/h/sheng/DOM-Q-NET/miniwob
  • Directly modify the base_url on line 33 of instance.py to
    "your-path-to-miniwob-plusplus"/html/miniwob
    In my case, base_url='file:///h/sheng/DOM-Q-NET/miniwob/html/miniwob/'

Run experiment

Experiment launch files are stored under runs For example,

cd runs/hard2medium9tasks/
sh run1.sh

will launch a 11 multi-task (social-media search-engine login-user enter-password click-checkboxes click-option enter-dynamic-text enter-text email-inbox-delete click-tab-2 navigation-tree) experiment.

Multitask Assumptions

State & Action restrictions

Item Maximum number of items
DOM tree leaves (action space) 160
DOM tree 200
Instruction tokens 16

Attribute embeddings & vocabulary

Attribute max vocabulary Embedding dimension
Tag 100 16
Text (shared with instructions) 600 48
Class 100 16
  • UNKnown tokens
    These are assigned to a random vector such that the cosine distance with the text attribute can yield 1.0 for the direct alignment.

Acknowledgement

Credit to Dopamine for the implementation of prioritized replay used in dstructs/dopamine_segtree.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].