按年被提到
20212021 · 2 次2026
强化学习与智能体›深度强化学习与世界模型·arXiv:2103.15793 · cs.RO

LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

Arthur Allshire, Roberto Martín-Martín, Charles Lin, Shawn Manuel, Silvio Savarese, Animesh Garg · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-04-04 · 最近 2021-07-11
2不同的人
2活跃月份
2讨论串
45被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar tasks or instances of the same task family impose latent manifold constraints on the most effective action space: the task family can be best solved with actions in a manifold of the entire action space of the robot. Combining these insights we present LASER, a method to learn latent action spaces for efficient reinforcement learning. LASER factorizes the learning problem into two sub-problems, namely action space learning and policy learning in the new action space. It leverages data from similar manipulation task instances, either from an offline expert or online during policy learning, and learns from these trajectories a mapping from the original to a latent action space. LASER is trained as a variational encoder-decoder model to map raw actions into a disentangled latent action space while maintaining action reconstruction and latent space dynamic consistency. We evaluate LASER on two contact-rich robotic tasks in simulation, and analyze the benefit of policy learning in the generated latent action space. We show improved sample efficiency compared to the original action space from better alignment of the action space to the task space, as we observe with visualizations of the learned action space manifold. Additional details: https://www.pair.toronto.edu/laser

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论hervature · 2021-07

“The algorithm is called LASER: https://arxiv.org/pdf/2103.15793v2.pdf Again, this is goal-post moving. Just because we are not there yet, it does not mean it will not happen. We just solved it for one door, now we need to generalize.”

Deep reinforcement learning is a waste of time (2019)原评论 ↗
被提交为 story · 1 次