Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

no code implementations • NeurIPS 2021 • Kate Rakelly, Abhishek Gupta, Carlos Florensa, Sergey Levine

Mutual information maximization provides an appealing formalism for learning representations of data.

Reinforcement Learning (RL) Representation Learning

Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning

no code implementations • 21 May 2020 • Michelle A. Lee, Carlos Florensa, Jonathan Tremblay, Nathan Ratliff, Animesh Garg, Fabio Ramos, Dieter Fox

Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state.

Goal-conditioned Imitation Learning

1 code implementation • NeurIPS 2019 • Yiming Ding, Carlos Florensa, Mariano Phielipp, Pieter Abbeel

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.

Imitation Learning Reinforcement Learning (RL)

Sub-policy Adaptation for Hierarchical Reinforcement Learning

no code implementations • ICLR 2020 • Alexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel

Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards.

Decision Making Hierarchical Reinforcement Learning +2

Adaptive Variance for Changing Sparse-Reward Environments

no code implementations • 15 Mar 2019 • Xingyu Lin, Pengsheng Guo, Carlos Florensa, David Held

Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration.

Self-supervised Learning of Image Embedding for Continuous Control

1 code implementation • 3 Jan 2019 • Carlos Florensa, Jonas Degrave, Nicolas Heess, Jost Tobias Springenberg, Martin Riedmiller

Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control.

Continuous Control Self-Supervised Learning

Reverse Curriculum Generation for Reinforcement Learning

no code implementations • 17 Jul 2017 • Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel

The robot is trained in reverse, gradually learning to reach the goal from a set of start states increasingly far from the goal.

reinforcement-learning Reinforcement Learning (RL)

Automatic Goal Generation for Reinforcement Learning Agents

1 code implementation • ICML 2018 • Carlos Florensa, David Held, Xinyang Geng, Pieter Abbeel

Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing.

reinforcement-learning Reinforcement Learning (RL)

Stochastic Neural Networks for Hierarchical Reinforcement Learning

2 code implementations • 10 Apr 2017 • Carlos Florensa, Yan Duan, Pieter Abbeel

Then a high-level policy is trained on top of these skills, providing a significant improvement of the exploration and allowing to tackle sparse rewards in the downstream tasks.

Hierarchical Reinforcement Learning reinforcement-learning +1