Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning — mentioned by gwern

Wed, 08 Jun 2016 19:41:51 GMT

You would get some boost if you use a NN factored to have game-specific module feeding into a universal game-playing NN: https://arxiv.org/abs/1511.06342 " Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning", Parisotto et al 2015 > The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its…

Paper and discussion history. A mention is not an endorsement.

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning · HackerPapers discussions

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning — mentioned by gwern