Related papers: Combining Model-Based and Model-Free Updates for T…
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…
Reinforcement learning (RL) and trajectory optimization (TO) present strong complementary advantages. On one hand, RL approaches are able to learn global control policies directly from data, but generally require large sample sizes to…
Model-free reinforcement learning (RL) is a powerful approach for learning control policies directly from high-dimensional state and observation. However, it tends to be data-inefficient, which is especially costly in robotic learning…
Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents…
We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control…
Reinforcement learning is a model-free optimal control method that optimizes a control policy through direct interaction with the environment. For reaching tasks that end in regulation, popular discrete-action methods are not well suited…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast…
This paper introduces a novel data-driven approach to design a linear quadratic regulator (LQR) using a reinforcement learning (RL) algorithm that does not require a system model. The key contribution is to perform policy iteration (PI) by…
Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such…
We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…
Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of…
This paper delves into designing stabilizing feedback control gains for continuous linear systems with unknown state matrix, in which the control is subject to a general structural constraint. We bring forth the ideas from reinforcement…
Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…
Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks. However, conventional RL approaches learn control policies through trial-and-error interactions with the…
We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…
We present one of the first algorithms on model based reinforcement learning and trajectory optimization with free final time horizon. Grounded on the optimal control theory and Dynamic Programming, we derive a set of backward differential…
Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…