Röder, FrankFrankRöderEppe, ManfredManfredEppeWermter, StefanStefanWermter2022-12-142022-12-142022-092022 IEEE International Conference on Development and Learning (ICDL 2022): 170-177978-1-6654-1311-4978-1-6654-1312-1978-1-6654-1310-7http://hdl.handle.net/11420/14360This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding of language in sensory data and actions. We address these issues with three contributions. We first present a mechanism for hindsight instruction replay utilizing expert feedback. Second, we propose a seq2seq model to generate linguistic hindsight instructions. Finally, we present a novel class of language-focused learning tasks. We show that hindsight instructions improve the learning performance, as expected. In addition, we also provide an unexpected result: We show that the learning performance of our agent can be improved by one third if, in a sense, the agent learns to talk to itself in a self-supervised manner. We achieve this by learning to generate linguistic instructions that would have been appropriate as a natural language goal for an originally unintended behavior. Our results indicate that the performance gain increases with the task-complexity.enreinforcement learninglanguage groundinginstruction followinghindsight instructionhuman-robot interactionInformatikTechnikIngenieurwissenschaftenConference Paper10.1109/ICDL53763.2022.99622072204.0430810.1109/ICDL53763.2022.9962207Conference Paper