Deep reinforcement learning algorithms for flexible job shop scheduling problems The introudce of code files agents the deep reinforcement learnging angents, including in DA3C/MPTD3/HMPSAC. environmet the scheduling environment of SO_DFJSP/MO_FJSSP/MO_DFJSP. network the trained policy network of agents. data the instance data for papers. result the result of all instance in data, including in tables/figures. rules scheduling rules for comparison reference code the relevance code for linear programming. single-objective dynamic problem(SO_DFJSP)-DA3C multi-objective static problem(MO_FJSSP)-MPTD3 multi-objective dynamic problem(MO_DFJSP)-HMPSAC