research
∙
02/21/2020
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
In this paper, we introduce a novel form of value function, Q(s, s'), th...
share
research
∙
05/20/2019
Perceptual Values from Observation
Imitation by observation is an approach for learning from expert demonst...
research
∙
05/21/2018
Imitating Latent Policies from Observation
We describe a novel approach to imitation learning that infers latent po...
research
∙
03/27/2018
Forward-Backward Reinforcement Learning
Goals for reinforcement learning problems are typically defined through ...
research
∙
11/21/2017
Transferring Agent Behaviors from Videos via Motion GANs
A major bottleneck for developing general reinforcement learning agents ...
research
∙
05/25/2017