How to train your robot with deep reinforcement learning: lessons we have learned
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
A survey of meta-reinforcement learning
While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …
machine learning, it is held back from more widespread adoption by its often poor data …
Meta-learning in neural networks: A survey
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
Replay-guided adversarial environment design
Deep reinforcement learning (RL) agents may successfully generalize to new settings if
trained on an appropriately diverse set of environment and task configurations …
trained on an appropriately diverse set of environment and task configurations …
Automatic curriculum learning for deep rl: A short survey
Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in
Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of …
Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of …
Offline meta-reinforcement learning with online self-supervision
Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks
with orders of magnitude less data than standard RL, but meta-training itself is costly and …
with orders of magnitude less data than standard RL, but meta-training itself is costly and …
Noveld: A simple yet effective exploration criterion
Efficient exploration under sparse rewards remains a key challenge in deep reinforcement
learning. Previous exploration methods (eg, RND) have achieved strong results in multiple …
learning. Previous exploration methods (eg, RND) have achieved strong results in multiple …
Explore, discover and learn: Unsupervised discovery of state-covering skills
Acquiring abilities in the absence of a task-oriented reward function is at the frontier of
reinforcement learning research. This problem has been studied through the lens of …
reinforcement learning research. This problem has been studied through the lens of …
One solution is not all you need: Few-shot extrapolation via structured maxent rl
While reinforcement learning algorithms can learn effective policies for complex tasks, these
policies are often brittle to even minor task variations, especially when variations are not …
policies are often brittle to even minor task variations, especially when variations are not …
Hierarchical reinforcement learning by discovering intrinsic options
We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-
agnostic options in a self-supervised manner while jointly learning to utilize them to solve …
agnostic options in a self-supervised manner while jointly learning to utilize them to solve …