Related papers: Raccoons vs Demons: multiclass labeled P300 datase…

We investigate the opportunities and challenges of running virtual reality (VR) studies remotely. Today, many consumers own head-mounted displays (HMDs), allowing them to participate in scientific studies from their homes using their own…

Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction…

Virtual reality is expected to play a significant role in the transformation of education and psychological studies. The possibilities for its application as a visual research method can be enhanced as established frameworks and toolkits…

This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks. This library is developed to implement recent state-of-the-art reinforcement learning models with extensible…

Recent research has shown that map raw pixels from a single front-facing camera directly to steering commands are surprisingly powerful. This paper presents a convolutional neural network (CNN) to playing the CarRacing-v0 using imitation…

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Collecting embodied interaction data at scale remains costly and difficult due to the limited accessibility of conventional interfaces. We present a gamified data collection framework based on Unity that combines procedural scene…

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…

Continuous brain-computer interfaces (BCIs) that decode motion trajectories from imagined movement offer intuitive motor control, yet how feedback modality and longitudinal training shape neural representations and decoding performance…

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…

In this paper, we present a dataset capturing diverse visual data formats that target varying luminance conditions. While RGB cameras provide nourishing and intuitive information, changes in lighting conditions potentially result in…

Training robots to perceive, act and communicate using multiple modalities still represents a challenging problem, particularly if robots are expected to learn efficiently from small sets of example interactions. We describe a learning…

The evaluation of object detection models is usually performed by optimizing a single metric, e.g. mAP, on a fixed set of datasets, e.g. Microsoft COCO and Pascal VOC. Due to image retrieval and annotation costs, these datasets consist…

In classifier (or regression) fusion the aim is to combine the outputs of several algorithms to boost overall performance. Standard supervised fusion algorithms often require accurate and precise training labels. However, accurate labels…

P300-based brain-computer interfaces (BCIs) are often trained per-user and per-application space. Training such models requires ground truth knowledge of target and non-target stimulus categories during model training, which imparts bias…

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…

Online reinforcement learning (RL) with sparse rewards poses a challenge partly because of the lack of feedback on states leading to the goal. Furthermore, expert offline data with reward signal is rarely available to provide this feedback…

Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to…

Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to explore the…