In this project I create agent for the BipedalWalker environment using the Proximal Policy Optimization (PPO) algorithm from the stablebaselines3 library. The agent is trained to navigate the BipedalWalker environment, which is a simulated robot with two legs.

Reinforcement Learning Scripts

BipedalWalker-V2 on varying terrains, with morphology adaptation

Own researches in reinforcement learning using openai-gym.

Bipedal Walker RL simulation using Gymnasium/Box2D with custom keyboard controls for experimentation.

Remember the sad Marvin from "Hitchhiker's guide to the galaxy"? In this project we train him to walk from the scratch using only pure python with numpy!

Using deep deterministic policy gradients for continuous control of a bipedal system

Neural network and Reinforcement learning algorithms for the Bipedal Walker problem

Discover the Passive-Code bot for passive income through arbitrage trading. Clone the repo and start automating your trades today! 🐙💻

Proximal Policy Optimization method in Pytorch

PyTorch application of reinforcement learning Advanced Policy Gradient algorithms in OpenAI BipedalWalker- PPO

Curiosity-driven PPO agent for BipedalWalker-v3 with Intrinsic Curiosity Module (ICM) for improved exploration in continuous control environments.

Utilizes Q-learning, DQN, and TD3 reinforcement learning algorithms to teach BipedalWalker to walk

[MATLAB] Various Passive Dynamic Walking Robot Simulation Code!

An ESP32 + Python controlled biped robot powered by servo motors.

ROS-based BD1 droid from Star Wars The Fallen Order

This is a Biped simulated on pybullet physics engine, walking

Programmatically Interpretable Reinforcement Learning

Solving openAI's game 'BipedalWalker-v2' with Deep Reinforcement Learning