Related papers: Tune to Learn: How Controller Gains Shape Robot Po…

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like…

Robot control problems are often structured with a policy function that maps state values into control values, but in many dynamic problems the observed state can have a difficult to characterize relationship with useful policy actions. In…

We propose a simple, practical and intuitive approach to improve the performance of a conventional controller in uncertain environments using deep reinforcement learning while maintaining safe operation. Our approach is motivated by the…

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

Reinforcement learning has been successfully applied to the problem of tuning PID controllers in several applications. The existing methods often utilize function approximation, such as neural networks, to update the controller parameters…

This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major…

Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance…

We present a method for efficient learning of control policies for multiple related robotic motor skills. Our approach consists of two stages, joint training and specialization training. During the joint training stage, a neural network…

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address…

Training robots with reinforcement learning (RL) typically involves heavy interactions with the environment, and the acquired skills are often sensitive to changes in task environments and robot kinematics. Transfer RL aims to leverage…

This paper presents an online reinforcement-learning framework for safe gain scheduling of a nonlinear quadcopter controller. Rather than learning thrust and torque commands directly, the proposed method selects gain vectors online from a…

For the task with complicated manipulation in unstructured environments, traditional hand-coded methods are ineffective, while reinforcement learning can provide more general and useful policy. Although the reinforcement learning is able to…

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent…

We investigate the problem of using a learning-based strategy to stabilize a synthetic toggle switch via an external control approach. To overcome the data efficiency problem that would render the algorithm unfeasible for practical use in…

Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system…

Dexterous manipulation has seen remarkable progress in recent years, with policies capable of executing many complex and contact-rich tasks in simulation. However, transferring these policies from simulation to real world remains a…

Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by…

Reinforcement learning is an emerging approach to control dynamical systems for which classical approaches are difficult to apply. However, trained agents may not generalize against the variations of system parameters. This paper presents…