Related papers: Efficient Real-World Autonomous Racing via Attenua…
Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…
We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without…
Reinforcement learning (RL) has enabled robust quadruped locomotion over complex terrain, but most learned controllers are trained offline with backpropagation in massively parallel simulation and deployed as fixed policies, limiting…
Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…
Modern learning-based locomotion controllers typically rely on fully trainable deep neural networks with a large number of parameters. This paper studies a different design point for end-to-end control: whether effective quadruped…
First-order Policy Gradient (FoPG) algorithms such as Backpropagation through Time and Analytical Policy Gradients leverage local simulation physics to accelerate policy search, significantly improving sample efficiency in robot control…
The behavior decision-making subsystem is a key component of the autonomous driving system, which reflects the decision-making ability of the vehicle and the driver, and is an important symbol of the high-level intelligence of the vehicle.…
Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settings. However, the success of adversarial optimization has…
Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs. Thus, various additional augmentations are…
Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for…
Reinforcement learning (RL) in continuous state-action spaces remains challenging in scientific computing due to poor sample efficiency and lack of pathwise physical consistency. We introduce Differential Reinforcement Learning…
Residential demand response programs aim to activate demand flexibility at the household level. In recent years, reinforcement learning (RL) has gained significant attention for these type of applications. A major challenge of RL algorithms…
Contemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types of missions they…
Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…
Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…
Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…
Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed…
Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…
Reinforcement Learning (RL) has achieved impressive results in robotics, yet high-performing pipelines remain highly task-specific, with little reuse of prior data. Offline Model-based RL (MBRL) offers greater data efficiency by training…