Reinforcement learning with bayesian classifiers: Efficient skill learning from outcome examples

[PDF] arxiv.org

Learning Task Agnostic Skills with Data-driven Guidance

E Klemsdal, S Herland, A Murad - arXiv preprint arXiv:2108.01869, 2021 - arxiv.org
To increase autonomy in reinforcement learning, agents need to learn useful behaviours
without reliance on manually designed reward functions. To that end, skill discovery …
被引用次数：1 相关文章 所有 4 个版本