相关论文: Learning a Unified Control Policy for Safe Falling

Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensitive criterion based…

Continuous control is a widely applicable area of reinforcement learning. The main players of this area are actor-critic methods that utilize policy gradients of neural approximators as a common practice. The focus of our study is to show…

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a…

Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data…

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

Adaptive falling and recovery skills greatly extend the applicability of robot deployments. In the case of legged mobile manipulators, the robot arm could adaptively stop the fall and assist the recovery. Prior works on falling and recovery…

Humanoid robots remain vulnerable to falls and unrecoverable failure states, limiting their practical utility in unstructured environments. While reinforcement learning has demonstrated stand-up behaviors, existing approaches treat recovery…

Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement…

We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control policy (e.g. one trained as a neural network) is paired with…

Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe dynamics learning, where sufficient exploration is…

Robotic loco-manipulation tasks often involve contact-rich interactions with the environment, requiring the joint modeling of contact force and robot position. However, recent visuomotor policies often focus solely on learning position or…

Many realistic robotics tasks are best solved compositionally, through control architectures that sequentially invoke primitives and achieve error correction through the use of loops and conditionals taking the system back to alternative…

We present a reformulation of a contact-implicit optimization (CIO) approach that computes optimal trajectories for rigid-body systems in contact-rich settings. A hard-contact model is assumed, and the unilateral constraints are imposed in…

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.…

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, facilitates a better understanding of an agent's decisions. We tackle this problem in the options…

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency. An AC based policy optimization process is iterative and needs to…

In order for autonomous vehicles to become a part of the Intelligent Transportation Ecosystem, they are required to guarantee a particular level of safety. For that to happen a safe vehicle control algorithms need to be developed, which…

Learning how to learn efficiently is a fundamental challenge for biological agents and a growing concern for artificial ones. To learn effectively, an agent must regulate its learning speed, balancing the benefits of rapid improvement…

This work is concerned with solving neural network-based feedback controllers efficiently for optimal control problems. We first conduct a comparative study of two prevalent approaches: offline supervised learning and online direct policy…

Safe control methods are often intended to behave safely even in worst-case human uncertainties. However, humans may exploit such safety-first systems, which results in greater risk for everyone. Despite their significance, no prior work…