Related papers: MuJoCoUni:Persistent Batched Runtime Primitives fo…

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

The current event display system in the offline software of Jiangmen Underground Neutrino Observatory Experiment(JUNO) is based on the ROOT EVE package. We use Unity, a renowned game engine, to improve its performance and make it available…

Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCodeReasoner, a…

Security is one of the main challenges of the Internet of Things (IoT). IoT devices are mainly powered by low-cost microcontrollers (MCUs) that typically lack basic hardware security mechanisms to separate security-critical applications…

The general-purpose self-adapting Monte Carlo (MC) event generator/simulator mFOAM (standing for mini-FOAM) is a new compact version of the FOAM program, with a slightly limited functionality with respect to its parent version. On the other…

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…

Parallel input performance issues are often neglected in large scale parallel applications in Computational Science and Engineering. Traditionally, there has been less focus on input performance because either input sizes are small (as in…

This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine. By comparing the performances of the Hindsight Experience…

Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to new tasks by training on data from a set of different tasks. Context-based approaches utilize a history of state-action-reward transitions --…

A long-standing objective in humanoid robotics is the realization of versatile agents capable of following diverse multimodal instructions with human-level flexibility. Despite advances in humanoid control, bridging high-level multimodal…

The iterative and incremental nature of software development using models typically makes a model of a system incomplete (i.e., partial) until a more advanced and complete stage of development is reached. Existing model execution approaches…

Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all possible situations, many methods collect additional data during online fine-tuning to improve performance.…

New ideas in distributed systems (algorithms or protocols) are commonly tested by simulation, because experimenting with a prototype deployed on a realistic platform is cumbersome. However, a prototype not only measures performance but also…

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…

Quadrupedal locomotion is a complex, open-ended problem vital to expanding autonomous vehicle reach. Traditional reinforcement learning approaches often fall short due to training instability and sample inefficiency. We propose a novel…

Quadruped mobile manipulators offer strong potential for agile loco-manipulation but remain difficult to control and transfer reliably from simulation to reality. Reinforcement learning (RL) shows promise for whole-body control, yet most…

We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with…

Advances in reinforcement learning have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We…

Proximal Policy Optimization (PPO) is widely used in continuous control due to its robustness and stable training, yet it remains sample-inefficient in tasks with expensive interactions and high-dimensional action spaces. This paper…

Extracting actionable insight from complex unlabeled scientific data is an open challenge and key to unlocking data-driven discovery in science. Complementary and alternative to supervised machine learning approaches, unsupervised…