Watch chenglijie1015/els

Watch chenglijie1015/mindrl forked from MindSpore Lab/mindrl

MindSpore Reinforcement是一个开源的强化学习框架，支持使用强化学习算法对agent进行分布式训练。

Watch chenglijie1015/DI-engine forked from OpenDILab开源决策智能平台/DI-engine

OpenDILab决策智能引擎 https://github.com/opendilab/DI-engine

Watch chenglijie1015/ICM-PPO-implementation

Watch chenglijie1015/icm

Watch chenglijie1015/automatic-sokoban-solver

Watch chenglijie1015/sokobanAI2

Watch chenglijie1015/RU-RL-Sokoban

Watch chenglijie1015/sokoban-rl

Watch chenglijie1015/sokoban2