Clean single-file implementation of offline RL algorithms in JAX

A Decision Transformer for solving optimal EV charging problems using offline data.

In this repository, we explore the application of Transformer-based Reinforcement Learning approaches to solve complex real-world energy management problems using the CityLearn environment (Challenge 2022 and 2023).

A collection of my implemented advanced & complex RL agents for games like Soccer, Street Fighter, Mortal Kombat, Rubik's Cube, Vizdoom, Montezuma, Kungfu-master, Super-Mario-bros, HalfCheetah and more by implementing advanced DRL concepts like decision transformers, RND, MARL, A3C, ICM & sample_factory. To see my other rl agents please visit

Training a stock exchange agent with Reinforcement Learning algorithms and Decision Transformer.

Master Thesis Project

Survey on RL via. Sequence Modeling using Decision Transformer

Decision Transformer with GTrXL backbone and World Model auxiliary training, plus C++/AVX2 batched env

Solving TSP problem using Behavioral Cloning. A comparative study of a simple MLP and a Decision Transformer for the Traveling Salesman Problem (TSP).

Pytorchを用いた強化学習のユースケース集(A2C、PPO、SAC、MPC、MBPO、CQL、Dreamer、Decision Transformer)

An LLM-free, action-grounded, locally-learning PC agent with dual-memory architecture (skill registry + Action Transformer).