25 citations · 60 across the 13 of their papers we have counts for
6 papers · 1 filter
On Value Discrepancy of Imitation Learning
Tian Xu, Ziniu Li, Yang Yu
Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised l…
Learning Action-Transferable Policy with Action Embedding
Yu Chen, Yingfeng Chen, Zhipeng Hu +4
Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different sta…
Knowledge-augmented Column Networks: Guiding Deep Learning with Advice
Mayukh Das, Devendra Singh Dhami, Yang Yu +2
Recently, deep models have had considerable success in several tasks, especially with low-level representations. However, effective learning from sparse noisy samples is a major ch…
Reinforcement Learning Experience Reuse with Policy Residual Representation
Wen-Ji Zhou, Yang Yu, Yingfeng Chen +4
Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be st…
Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice
Mayukh Das, Yang Yu, Devendra Singh Dhami +2
Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with…
Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
Ruo-Ze Liu, Haifeng Guo, Xiaozhong Ji +5
Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our discovery that an abstrac…