Author: marek.k

LANRO is a platform to study language-conditioned reinforcement learning. No. of environments: 4807

Learning Event-triggered Control from Data through Joint Optimization. No. of environments: 947

lilGym is a benchmark for language-conditioned RL in visual environments with executable Python annotations.. No. of environments: 4

A diverse benchmark for evaluating AI agents’ ability to learn interactively from natural language feedback across tasks like navigation, poem writing, and robot control.. No. of environments: 19

A collection of Open AI Gym environments ment to simualte logistical problems such as routing, container filling and supply chain. No. of environments: 1