The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Обновлено 2024-09-14 20:00:24 +03:00
​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.
Обновлено 2024-07-24 23:43:42 +03:00
A learning environment for man-made Interactive Fiction games.
Обновлено 2024-05-02 05:48:15 +03:00
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
Обновлено 2024-02-23 11:45:58 +03:00
Visuomotor policies from event-based cameras through representation learning and reinforcement learning. Accompanies our paper: https://arxiv.org/abs/2103.00806
Обновлено 2023-08-15 00:50:21 +03:00
Logarithmic Reinforcement Learning
Обновлено 2023-03-25 04:36:23 +03:00
DOTS compatible version of ML-Agents
Обновлено 2021-10-04 23:09:24 +03:00
Obstacle Tower Environment
Обновлено 2020-07-29 04:08:41 +03:00
Demo project using tabular Q-learning algorithm
Обновлено 2018-01-12 05:11:34 +03:00