Giter Site home page Giter Site logo

linghengmeng / 4_room_world_environment Goto Github PK

View Code? Open in Web Editor NEW
6.0 1.0 3.0 5.01 MB

This repository provides a simulation of 4-Room-World environment.

License: MIT License

Python 100.00%
reinforcement-learning hierarchical-reinforcement-learning openai-gym-environments continuous-control gridworld-environment 4-room-grid-world

4_room_world_environment's Introduction

4_Room_World_Environment

This repository provides a simulation of 4-Room-World environment based on V-REP, and the virtual environments implemented in this repository share the same interfaces with OpenAi Gym.

There are in totall 4 Types of 4-Room-World Environment with various complexities implemented in this repository. For more detail information on these virtual environments, please refer to 4 Types of 4-Room-World Environment.

Step 1: Create 4-Room-World Scene (Optional)

FourRoomScene folder contains files to create a scene using V-REP api(If you do not have V-REP, please download from V-REP).

  • 4room_world_models: V-REP models used to create a scene

  • VrepRemoteApiBindings: V-REP dynamic lib and api-script

  • CSV files: specify position of loaded objects

     * "wall_brick_location.csv": position of wall brick
     * "floor_tile_location.csv": position of wall floor tile
     * "hallway_location.csv": position of hallway
     * "goal_location.csv": position of goal
     * "standing_participant_location.csv": initial position of standing participant which is static.
    
  • Script to create a scene: create_4room_world.py

  • V-REP scene created by script: 4_room_world.ttt

                                           

                                                                            Figure 1. 4Room World Screenshots

Step 2: Load Scene to V-REP

Load scene pre-created or scene created by yourself into V-REP.

  • FourRoomGridWorld & FourRoomContinuousWorld: 4_room_world.ttt
  • FourRoomOverheadVisionWorld: 4_room_overhead_vision_world.ttt
  • FourRoomFirstPersonVisionWorld: 4_room_first_person_vision_world.ttt

Step 3: Choose 4-Room-World Virtual Environment

For detailed information on these virtual environments, please refer to 4 Types of 4-Room-World Environment.

  1. FourRoomGridWorld
  2. FourRoomContinuousWorld
  3. FourRoomOverheadVisionWorld
  4. FourRoomFirstPersonVisionWorld

Step 4: Use 4-Room-World Virtual Environment as You Using OpenAi Gym

Demo scripts on how to use these virtual environments can be found in:

  1. interaction_participant_and_4room_grid_world_env.py
  2. interaction_participant_and_4room_continuous_world_env.py

You are welcom to contribute to this reposity and make it more versatile :)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.