activity
20122022
most citedRisk-Aware Transfer in Reinforcement Learning using Successor Features

9 citations · 10 across the 6 of their papers we have counts for

collaborators

8 papers

cs.LG2022

Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps

Kuilin Chen, Chi-Guhn Lee

Learning a new task from a handful of examples remains an open challenge in machine learning. Despite the recent progress in few-shot learning, most methods rely on supervised pret…

cs.LG2022

Meta-free few-shot learning via representation learning with weight averaging

Kuilin Chen, Chi-Guhn Lee

Recent studies on few-shot classification using transfer learning pose challenges to the effectiveness and efficiency of episodic meta-learning algorithms. Transfer learning approa…

cs.LG20219 cited

Risk-Aware Transfer in Reinforcement Learning using Successor Features

Michael Gimelfarb, André Barreto, Scott Sanner +1

Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer le…

cs.LG20211 cited

Attentive Gaussian processes for probabilistic time-series generation

Kuilin Chen, Chi-Guhn Lee

The transduction of sequence has been mostly done by recurrent networks, which are computationally demanding and often underestimate uncertainty severely. We propose a computationa…

cs.LG2020

ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning

Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee

Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus o…

cs.LG2020

Bayesian Experience Reuse for Learning from Multiple Demonstrators

Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee

Learning from demonstrations (LfD) improves the exploration efficiency of a learning agent by incorporating demonstrations from experts. However, demonstration data can often come…