We present Bayesian Controller Fusion (BCF): a hybrid control strategy that combines the
strengths of traditional hand-crafted controllers and model-free deep reinforcement learning …

Deep reinforcement learning has recently seen huge success across multiple areas in the
robotics domain. Owing to the limitations of gathering real-world data, ie, sample inefficiency …

Substantial advancements to model-based reinforcement learning algorithms have been
impeded by the model-bias induced by the collected data, which generally hurts …

The vision-based reinforcement learning (RL) has achieved tremendous success. However,
generalizing vision-based RL policy to unknown test environments still remains as a …

While deep reinforcement learning techniques have recently produced considerable
achievements on many decision-making problems, their use in robotics has largely been …

Model-based deep reinforcement learning has achieved success in various domains that
require high sample efficiencies, such as Go and robotics. However, there are some …

In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by
maximizing an exogenous reward signal while interacting with its environment. In real world …

We present Residual Policy Learning (RPL): a simple method for improving
nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in …

Most reinforcement learning (RL) algorithms assume online access to the environment, in
which one may readily interleave updates to the policy with experience collection using that …

The process of learning a manipulation task depends strongly on the action space used for
exploration: posed in the incorrect action space, solving a task with reinforcement learning …