sharpesharpe is a unified, interactive, general-purpose environment for backtesting or applying machine learning(supervised learning and reinforcement learning) in the context of quantitative trading
gym-hybridCollection of OpenAI parametrized action-space environments.
AI4UAI4U is a multi-engine plugin (Unity and Godot) that allows you to specify agents with reinforcement learning visually. Non-Player Characters (NPCs) of games can be designed using ready-made components. In addition, AI4U has a low-level API that allows you to connect the agent to any algorithm made available in Python by the reinforcement learni…
simple-playgroundsSimulator for Reinforcement Learning and AI. 2D environments with physics and interactive entities. Agents with rich sensors and actuators.
magicalThe MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)
modelicagymModelica models integration with Open AI Gym
bark-mlGym environments and agents for autonomous driving.
SNACSimultaneous Navigation and Construction
FlashRLNo description or website provided.
Pontryagin-Differentiable-ProgrammingA unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.
realantRealAnt robot platform for low-cost, real-world reinforcement learning
rlberryAn easy-to-use reinforcement learning library for research and education.
multi car racingAn OpenAI Gym environment for multi-agent car racing based on Gym's original car racing environment.