research
∙
09/26/2022
Understanding Hindsight Goal Relabeling Requires Rethinking Divergence Minimization
Hindsight goal relabeling has become a foundational technique for multi-...
share
research
∙
08/23/2018
Transfer Learning for Estimating Causal Effects using Neural Networks
We develop new algorithms for estimating heterogeneous treatment effects...
research
∙
03/03/2018
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
We consider the problem of exploration in meta reinforcement learning. T...
research
∙
02/13/2018
Evolved Policy Gradients
We propose a meta-learning approach for learning gradient-based reinforc...
research
∙
03/21/2017
One-Shot Imitation Learning
Imitation learning has been commonly applied to solve different tasks in...
research
∙
03/06/2017
Third-Person Imitation Learning
Reinforcement learning (RL) makes it possible to train agents capable of...
research
∙
07/03/2015