22 citations · 22 across the 2 of their papers we have counts for
4 papers · 1 filter
Provably Efficient Kernelized Q-Learning
Shuang Liu, Hao Su
We propose and analyze a kernelized version of Q-learning. Although a kernel space is typically infinite-dimensional, extensive study has shown that generalization is only affected…
Model Imitation for Model-Based Reinforcement Learning
Yueh-Hua Wu, Ting-Han Fan, Peter J. Ramadge +1
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollout…
Multi-task Batch Reinforcement Learning with Metric Learning
Jiachen Li, Quan Vuong, Shuang Liu +5
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks…
How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
Quan Vuong, Sharad Vikram, Hao Su +2
Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this succes…