-
AGH University of Krakow
- Kraków, Poland
- https://macmacal.github.io/
🧠 DeepRL
EAGERx is a physics engine abstraction layer for reinforcement learning. EAGERx allows switching between simulators and reality with a single line of code, supports action and observation processin…
A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning
Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
FinRL: Financial Reinforcement Learning. 🔥
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
Benchmarking RL generalization in an interpretable way.
Obstacle Tower Environment
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Agent Learning Framework https://alf.readthedocs.io
Massively parallel rigidbody physics simulation on accelerator hardware.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
A collection of robotics simulation environments for reinforcement learning
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Generative Agents: Interactive Simulacra of Human Behavior
A curated list of resources about Machine Learning for Robotics
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.
Reinforcement Learning Environments for Omniverse Isaac Gym
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
Code used to train an augmented auto-encoder (aka denoising auto-encoder with more augmentations) for the DonkeyCar simulator.