\n | <\/td>\n | def<\/span> muzero<\/span>(config<\/span>: MuZeroConfig<\/span>):<\/td>\n <\/tr>\n \n | <\/td>\n | storage<\/span> =<\/span> SharedStorage<\/span>()<\/td>\n <\/tr>\n \n | <\/td>\n | replay_buffer<\/span> =<\/span> ReplayBuffer<\/span>(config<\/span>)<\/td>\n <\/tr>\n \n | <\/td>\n | \n<\/td>\n <\/tr>\n | \n | <\/td>\n | for<\/span> _<\/span> in<\/span> range<\/span>(config<\/span>.num_actors<\/span>):<\/td>\n <\/tr>\n \n | <\/td>\n | launch_job<\/span>(run_selfplay<\/span>, config<\/span>, storage<\/span>, replay_buffer<\/span>)<\/td>\n <\/tr>\n \n | <\/td>\n | \n<\/td>\n <\/tr>\n | \n | <\/td>\n | train_network<\/span>(config<\/span>, storage<\/span>, replay_buffer<\/span>)<\/td>\n <\/tr>\n \n | <\/td>\n | \n<\/td>\n <\/tr>\n | \n | <\/td>\n | return<\/span> storage<\/span>.latest_network<\/span>()<\/td>\n <\/tr>\n<\/table>\n\n\n <\/div>\n\n <\/div>\n<\/div>\n\n <\/div>\n | | | | | | |