Reinforcement Learning
Latent Exploration for Reinforcement Learning
While this unstructured exploration has proven successful in numerous tasks, it can be suboptimal for overactuated systems. When multiple actuators, such as motors or muscles, drive behavior, uncorrelated perturbations risk diminishing each other's effect, or modifying the behavior in a task-irrelevant way. While solutions to introduce time correlation across action perturbations exist, introducing correlation across actuators has been largely ignored.
One Demonstration is Enough to Learn Robot Policies
Sequential decision-making problems typically require significant human supervision and data.
Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
Honguk Woo is the corresponding author.
Supplementary Material to Bi-Level Offline Policy Optimization with Limited Exploration
The "replay" subset consists of samples
Bi-Level Offline Policy Optimization with Limited Exploration
Subsequently, at the upper level, the policy aims to maximize a conservative value estimate from the confidence set formed at the lower level.
Model-Free Active Exploration in Reinforcement Learning
We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be collected to identify a nearly-optimal policy.
