Related papers: SimLauncher: Launching Sample-Efficient Real-world…
Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world…
Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots.…
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…
Reinforcement Learning (RL) is a machine learning framework for artificially intelligent systems to solve a variety of complex problems. Recent years has seen a surge of successes solving challenging games and smaller domain problems,…
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor…
Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain,…
Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real…
Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has…
Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…
While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (for…
Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning…
Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial…
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm…
Sim2Real aims at training policies in high-fidelity simulation environments and effectively transferring them to the real world. Despite the developments of accurate simulators and Sim2Real RL approaches, the policies trained purely in…
Reinforcement learning (RL) algorithms hold the promise of enabling autonomous skill acquisition for robotic systems. However, in practice, real-world robotic RL typically requires time consuming data collection and frequent human…
This thesis work presents a more efficient and effective approach to training control-related tasks for humanoid robots using Reinforcement Learning (RL). The traditional RL methods are limited in adapting to real-world environments,…
Teaching robots dexterous manipulation skills often requires collecting hundreds of demonstrations using wearables or teleoperation, a process that is challenging to scale. Videos of human-object interactions are easier to collect and…
We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world…
Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages,…
Deep Reinforcement Learning (RL) can yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of…