-
Human-centric Dialog Training via Offline Reinforcement Learning
How can we train a dialog model to produce better conversations by learn...
10/12/2020 ∙ by Natasha Jaques, et al. ∙
4
∙
share
read it
-
Multi-agent Social Reinforcement Learning Improves Generalization
Social learning is a key component of human and animal intelligence. By ...
10/01/2020 ∙ by Kamal Ndousse, et al. ∙
35
∙
share
read it
-
Hierarchical Reinforcement Learning for Open-Domain Dialog
Open-domain dialog generation is a challenging problem; maximum likeliho...
09/17/2019 ∙ by Abdelrhman Saleh, et al. ∙
5
∙
share
read it
-
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Most deep reinforcement learning (RL) systems are not able to learn effe...
06/30/2019 ∙ by Natasha Jaques, et al. ∙
9
∙
share
read it
-
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
Building an open-domain conversational agent is a challenging problem. C...
06/21/2019 ∙ by Asma Ghandeharioun, et al. ∙
3
∙
share
read it
-
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we...
06/10/2019 ∙ by David Rolnick, et al. ∙
1
∙
share
read it
-
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communicat...
10/19/2018 ∙ by Natasha Jaques, et al. ∙
0
∙
share
read it
-
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
We derive a new intrinsic social motivation for multi-agent reinforcemen...
10/19/2018 ∙ by Natasha Jaques, et al. ∙
0
∙
share
read it
-
Learning via social awareness: improving sketch representations with facial feedback
In the quest towards general artificial intelligence (AI), researchers h...
02/13/2018 ∙ by Natasha Jaques, et al. ∙
0
∙
share
read it
-
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
This paper proposes a general method for improving the structure and qua...
11/09/2016 ∙ by Natasha Jaques, et al. ∙
0
∙
share
read it
