Coder Social home page Coder Social logo

real_time_rl_project's People

Contributors

codebro634 avatar nicolasfroehlich avatar ymahlau avatar

Stargazers

avatar

Watchers

avatar

Forkers

nicolasfroehlich

real_time_rl_project's Issues

Experiments TODO List

    • Acrobot-v1 (max_steps 100000, eval every 500 steps)
        • Vanilla SAC (seed 0-4)
        • Vanllia RTAC (seed 0-4)
        • Vanlla SAC in RTMDP (seed 0-4)
    • CartPole-v1 (max_steps 100000, eval every 500 steps, number of iterations per eval: 20)
        • Vanilla SAC (seed 0-4)
        • Vanllia RTAC (seed 0-4)
        • Vanlla SAC in RTMDP (seed 0-4)
        • SAC in RTMDP with Output Normalization (seed 0-4)
        • RTAC with Output Normalization (seed 0-4)
        • SAC in RTMDP with Double Value (seed 0-4)
        • RTAC with Double Value (seed 0-4)
        • SAC in RTMDP with Target Network (seed 0-4)
        • RTAC with Target Network (seed 0-4)
        • RTAC with shared Parameters (seed 0-4)
    • LunarLander-v2 (max_steps 300000, eval every 500 steps)
        • Vanilla SAC (seed 0-4)
        • Vanllia RTAC (seed 0-4)
        • Vanlla SAC in RTMDP (seed 0-4)
        • SAC in RTMDP with Output Normalization (seed 0-4)
        • RTAC with Output Normalization (seed 0-4)
        • SAC in RTMDP with Double Value (seed 0-4)
        • RTAC with Double Value (seed 0-4)
        • SAC in RTMDP with Target Network (seed 0-4)
        • RTAC with Target Network (seed 0-4)
        • RTAC with shared Parameters (seed 0-4)
        • RTAC with everything (seed 0-4)
        • SAC with everything (seed 0-4)
        • SAC in RTMDP with everything (seed 0-4)
    • RTAC shared + normalization
        • LunarLander
        • CartPole
    • LunarLanderStepSize (All Vanilla Versions)
        • RTAC
          1. step_size 1, train for 100000, eval every 1000 (seed 0-2)
          2. step size 0.3, train for 100000, eval every 1000 (seed 0-2)
          3. step size 0.1, train for 100000, eval every 1000 (seed 0-2)
          4. step size 0.03, train for 100000, eval every 1000 (seed 0-2)
          5. step size 0.01, train for 100000, eval every 1000 (seed 0-2)
        • SAC in RTMDP
          1. step_size 1, train for 100000, eval every 1000 (seed 0-2)
          2. step size 0.3, train for 100000, eval every 1000 (seed 0-2)
          3. step size 0.1, train for 100000, eval every 1000 (seed 0-2)
          4. step size 0.03, train for 100000, eval every 1000 (seed 0-2)
          5. step size 0.01, train for 100000, eval every 1000 (seed 0-2)
        • SAC
          1. step_size 1, train for 100000, eval every 1000 (seed 0-2)
          2. step size 0.3, train for 100000, eval every 1000 (seed 0-2)
          3. step size 0.1, train for 100000, eval every 1000 (seed 0-2)
          4. step size 0.03, train for 100000, eval every 1000 (seed 0-2)
          5. step size 0.01, train for 100000, eval every 1000 (seed 0-2)

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.