Related papers: Modifying RL Policies with Imagined Actions: How P…

For robots to successfully transition from lab settings to everyday environments, they must begin to reason about the risks associated with their actions and make informed, risk-aware decisions. This is particularly true for robots…

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

On-policy reinforcement learning (RL) algorithms have demonstrated great potential in robotic control, where effective exploration is crucial for efficient and high-quality policy learning. However, how to encourage the agent to explore the…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…

We consider the Imitation Learning (IL) setup where expert data are not collected on the actual deployment environment but on a different version. To address the resulting distribution shift, we combine behavior cloning (BC) with a planner…

When limited by their own morphologies, humans and some species of animals have the remarkable ability to use objects from the environment toward accomplishing otherwise impossible tasks. Robots might similarly unlock a range of additional…

Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists. However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide…

Deep reinforcement learning (RL) has shown immense potential for learning to control systems through data alone. However, one challenge deep RL faces is that the full state of the system is often not observable. When this is the case, the…

A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training. In this paper, we approach this challenge through the following invariance principle: an agent…

Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or…

Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies. However, it can lead to undesirable or catastrophic outcomes when learning online in safety-critical environments. In…

Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising…

In this paper, we propose the use of generative artificial intelligence (AI) to improve zero-shot performance of a pre-trained policy by altering observations during inference. Modern robotic systems, powered by advanced neural networks,…

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

The multiagent-based participatory simulation features prominently in urban planning as the acquired model is considered as the hybrid system of the domain and the local knowledge. However, the key problem of generating realistic agents for…

Machine learning techniques have enabled robots to learn narrow, yet complex tasks and also perform broad, yet simple skills with a wide variety of objects. However, learning a model that can both perform complex tasks and generalize to…

Contact-rich manipulation tasks are commonly found in modern manufacturing settings. However, manually designing a robot controller is considered hard for traditional control methods as the controller requires an effective combination of…

In reinforcement learning, if the agent's reward differs from the designers' true utility, even only rarely, the state distribution resulting from the agent's policy can be very bad, in theory and in practice. When RL policies would devolve…