DeepSynth: Automata synthesis for automatic task segmentation in deep reinforcement learning
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorith...
| Автори: | , , , , |
|---|---|
| Формат: | Conference item |
| Мова: | English |
| Опубліковано: |
Association for the Advancement of Artificial Intelligence
2021
|