activity
20172020
most citedDeep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection

52 citations · 71 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG20204 cited

f-IRL: Inverse Reinforcement Learning via State Marginal Matching

Tianwei Ni, Harshit Sikchi, Yufei Wang +3

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method…

cs.LG2020

Weakly-Supervised Reinforcement Learning for Controllable Behavior

Lisa Lee, Benjamin Eysenbach, Ruslan Salakhutdinov +2

Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space…

cs.LG2020

Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling

Yaqiong Li, Xuhui Fan, Ling Chen +3

The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage…

cs.LG2019

Efficient Exploration via State Marginal Matching

Lisa Lee, Benjamin Eysenbach, Emilio Parisotto +3

Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions…

cs.LG2019

Embodied Multimodal Multitask Learning

Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov +2

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tas…

cs.LG2018

On the Complexity of Exploration in Goal-Driven Navigation

Maruan Al-Shedivat, Lisa Lee, Ruslan Salakhutdinov +1

Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of th…