Related papers: Learning on the Fly: Rapid Policy Adaptation via D…
Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training…
Distribution shift in imitation learning refers to the problem that the agent cannot plan proper actions for a state that has not been visited during the training. This problem can be largely attributed to the inherently narrow state-action…
Model-free policy learning has enabled robust performance of complex tasks with relatively simple algorithms. However, this simplicity comes at the cost of requiring an Oracle and arguably very poor sample complexity. This renders such…
In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the…
Direct data-driven design methods for the linear quadratic regulator (LQR) mainly use offline or episodic data batches, and their online adaptation has been acknowledged as an open problem. In this paper, we propose a direct adaptive method…
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…
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may…
Practitioners often rely on compute-intensive domain randomization to ensure reinforcement learning policies trained in simulation can robustly transfer to the real world. Due to unmodeled nonlinearities in the real system, however, even…
This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. We propose a combination of a Reinforcement Learning (RL) based policy in the outer loop suitably chosen to ensure…
Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies…
While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the…
Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can…
End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment. Yet…
Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with…
Simulation parameter settings such as contact models and object geometry approximations are critical to training robust robotic policies capable of transferring from simulation to real-world deployment. Previous approaches typically…
We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle with active suspensions designed for traversing rough terrain. While related research primarily focuses on lightweight robots with electric…
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and…
While Reinforcement Learning (RL) has achieved remarkable progress in legged locomotion control, it often suffers from performance degradation in out-of-distribution (OOD) conditions and discrepancies between the simulation and the real…
Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…
One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies. Robustness is critical when the…