Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning

Sample efficiency in reinforcement learning (RL) is an elusive goal. Recent attempts at increasing the sample efficiency of RL implementations have focused to a large extent on incorporating models into the training process: [25, 6, 28, 3, 12, 26, 9, 5, 20]. The models encapsulate knowledge explicitly, complementing the experiences that are gained by sampling from the RL environment. Another means towards increasing the availability of samples for a reinforcement learner is by tilting the training towards one that will better transfer to related tasks: if the training process is sufficiently well adapted to more than one task, then the training of a particular task should be able to benefit from samples from the other related tasks. This idea was explored a decade ago in [13] and has been gaining traction ever since, as researchers try to increase the reach of deep reinforcement learning from its comfortable footing in solving games outrageously well to solving other important problems.