A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.

An environment of the board game Go using OpenAI's Gym API

Reinforcement Learning Agents Trained in the CARLA Simulator

Code for reproducing results in ICML 2020 paper "PackIt: A Virtual Environment for Geometric Planning"

OpenAI Gym environment designed for training RL agents to control the flight of a two-dimensional drone.

A collection of several Deep Reinforcement Learning techniques (Deep Q Learning, Policy Gradients, ...), gets updated over time.

A graphical interface for reinforcement learning and gym-based environments.

General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems

Implementations of various RL and Deep RL algorithms in TensorFlow, PyTorch and Keras.

Beer Game implemented as an OpenAI gym environment.

Simple PyTorch implementation of Deep Q-learning Algorithm to play Lunar Lander.

OpenAI Gym environment designed for training RL agents to balance double CartPole.

Simple Minimalistic Gridworld Environment for OpenAI Gym (Simple-MiniGrid)

Code for generating data in ICML 2020 paper "PackIt: A Virtual Environment for Geometric Planning"

Training material - An RL playground to test Karpathy's great tutorial on Policy Gradients.

Solution to the Deep RL Bootcamp labs from UC Berkeley

Course work of Reinforcement-Learning-CS6700

👾 RL agent that completes the Battle City arcade game

An implementation from the state-of-the-art family of reinforcement learning algorithms Proximal Policy Optimization using normalized Generalized Advantage Estimation and optional batch mode training. The loss function incorporates an entropy bonus.

I am trying to implement various AI algorithms on various environments (like OpenAI-gym) as I learned my toward the safe AI