A deep Q learning demonstration using Google Tensorflow
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation learning, and training orchestration. It provides a library of standardized learning algorithms used to benchmark and replicate research results, alongside a deep learning policy framework for constructing neural network architectures such as multi-layer perceptrons, convolutional networks, and long short-term memory networks. The project includes a specialized imitation learning toolkit that enables agents to mimic expert behavior through behavior cloning and generative adversarial
ChainerRL is a deep reinforcement learning library built on top of Chainer.
The main features of chainer/chainerrl are: Algorithm Implementations, Reinforcement Learning Frameworks.
Open-source alternatives to chainer/chainerrl include: resibots/blackdrops — Code for the Black-DROPS algorithm: "Black-Box Data-efficient Policy Search for Robotics", IROS 2017/ICRA 2018. nivwusquorum/tensorflow-deepq — A deep Q learning demonstration using Google Tensorflow. instadeepai/jumanji — 🕹️ A diverse suite of scalable reinforcement learning environments in JAX. openai/baselines — Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation… kaixhin/atari — Persistent advantage learning dueling double DQN for the Arcade Learning Environment. rlcode/reinforcement-learning — Minimal and Clean Reinforcement Learning Examples.