Skip to content
View kirarpit's full-sized avatar
🤗
🤗

Block or report kirarpit

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. plexwrap plexwrap Public

    A personalized year-in-review for Plex

    Python 27 2

  2. connect4 connect4 Public

    Solving board games like Connect4 using Deep Reinforcement Learning

    Python 33 4

  3. redefine redefine Public

    AI-powered word learning reimagined.

    TypeScript

  4. compiler-construction compiler-construction Public

    LOBO-C Compiler

    C++

  5. Robbie the soda-can-collecting robot... Robbie the soda-can-collecting robot (https://bit.ly/2MPUku5) trained with a deep RL algorithm, PPO, with the help of Ray RLlib.
    1
    import ray
    2
    from gym import spaces
    3
    from ray.rllib.env.multi_agent_env import MultiAgentEnv
    4
    import numpy as np
    5
    from ray.tune.registry import register_env
  6. klotski-deep-RL klotski-deep-RL Public

    Solving Klotski using deep reinforcement learning!

    Python 2