Related papers: Assessing Transferability from Simulation to Reali…

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

A seamless integration of robots into human environments requires robots to learn how to use existing human tools. Current approaches for learning tool manipulation skills mostly rely on expert demonstrations provided in the target robot…

The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling…

Learning for control can acquire controllers for novel robotic tasks, paving the path for autonomous agents. Such controllers can be expert-designed policies, which typically require tuning of parameters for each task scenario. In this…

Recently, reinforcement learning has achieved remarkable results in various domains, including robotics, games, natural language processing, and finance. In the financial domain, this approach has been applied to tasks such as portfolio…

Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during…

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…

Specifying tasks for robotic systems traditionally requires coding expertise, deep domain knowledge, and significant time investment. While learning from demonstration offers a promising alternative, existing methods often struggle with…

Simulation is used extensively in autonomous systems, particularly in robotic manipulation. By far, the most common approach is to train a controller in simulation, and then use it as an initial starting point for the real system. We…

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remarkably well to multiple different physical quadrotors. Our…

Simulation Optimization (SO) refers to the optimization of an objective function subject to constraints, both of which can be evaluated through a stochastic simulation. To address specific features of a particular simulation---discrete or…

This paper considers simulation-based optimization of the performance of a regime-switching stochastic system over a finite set of feasible configurations. Inspired by the stochastic fictitious play learning rules in game theory, we propose…

Deep reinforcement learning models are notoriously data hungry, yet real-world data is expensive and time consuming to obtain. The solution that many have turned to is to use simulation for training before deploying the robot in a real…

This paper explores transfer learning in heterogeneous multi-source environments with distributional divergence between target and auxiliary domains. To address challenges in statistical bias and computational efficiency, we propose a…

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to…

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot…

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…

Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment, and has become essential in mission-critical domains such as supply chains and industrial systems. However,…

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from…