Related papers: Sim-Anchored Learning for On-the-Fly Adaptation

The rapid growth of ride-hailing platforms has created a highly competitive market where businesses struggle to make profits, demanding the need for better operational strategies. However, real-world experiments are risky and expensive for…

Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track…

Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation"…

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Robotic cloth untangling requires progressively disentangling fabric by adapting pulling actions to changing contact and tension conditions. Because large-scale real-world training is impractical due to cloth damage and hardware wear,…

Reinforcement Learning (RL) agents often struggle in real-world applications where environmental conditions are non-stationary, particularly when reward functions shift or the available action space expands. This paper introduces MORPHIN, a…

Scalable multi-agent driving simulation requires behavior models that are both realistic and computationally efficient. We address this by optimizing the behavior model that controls individual traffic participants. To improve efficiency,…

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,…

Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a…

Simulation based learning often provides a cost-efficient recourse to reinforcement learning applications in robotics. However, simulators are generally incapable of accurately replicating real-world dynamics, and thus bridging the sim2real…

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. Domain Randomization (DR)…

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The…

Optimizing economic and public policy is critical to address socioeconomic issues and trade-offs, e.g., improving equality, productivity, or wellness, and poses a complex mechanism design problem. A policy designer needs to consider…

Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of…

Autonomous driving systems require comprehensive evaluation in safety-critical scenarios to ensure safety and robustness. However, such scenarios are rare and difficult to collect from real-world driving data, necessitating simulation-based…

In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low-…

There has been an increasing interest in 3D indoor navigation, where a robot in an environment moves to a target according to an instruction. To deploy a robot for navigation in the physical world, lots of training data is required to learn…

Legged locomotion is not just about mobility; it also encompasses crucial objectives such as energy efficiency, safety, and user experience, which are vital for real-world applications. However, key factors such as battery power consumption…

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…