184 citations · 542 across the 9 of their papers we have counts for
5 papers · 1 filter
Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Kate Rakelly, Abhishek Gupta, Carlos Florensa +1
Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accele…
Sub-policy Adaptation for Hierarchical Reinforcement Learning
Alexander C. Li, Carlos Florensa, Ignasi Clavera +1
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lowe…
Goal-conditioned Imitation Learning
Yiming Ding, Carlos Florensa, Mariano Phielipp +1
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is partic…
Self-supervised Learning of Image Embedding for Continuous Control
Carlos Florensa, Jonas Degrave, Nicolas Heess +2
Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to sol…
Automatic Goal Generation for Reinforcement Learning Agents
Carlos Florensa, David Held, Xinyang Geng +1
Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the…