TRPO-TensorFlow:纯TensorFlow中的信任区域策略优化（TRPO）

[{"title":"（ 11 个子文件 13KB ） TRPO-TensorFlow:纯TensorFlow中的信任区域策略优化（TRPO）","children":[{"title":"TRPO-TensorFlow-master","children":[{"title":".gitignore <span style='color:#111;'> 38B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 77B </span>","children":null,"spread":false},{"title":"net.py <span style='color:#111;'> 12.61KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 792B </span>","children":null,"spread":false},{"title":"trpo.py <span style='color:#111;'> 5.66KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 5.22KB </span>","children":null,"spread":false},{"title":"env.py <span style='color:#111;'> 706B </span>","children":null,"spread":false},{"title":"main.py <span style='color:#111;'> 1.00KB </span>","children":null,"spread":false},{"title":"ppo.py <span style='color:#111;'> 3.72KB </span>","children":null,"spread":false},{"title":"tagbardebug.log <span style='color:#111;'> 2.03KB </span>","children":null,"spread":false},{"title":"agent.py <span style='color:#111;'> 8.31KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]