With the latest developments in sensors, battery, and Artificial Intelligence (AI) technologies, robots can perform missions in unstructured environments (e.g., disaster sites). However, their adaptation speed is still slow due to their limited onboard computing capability and dynamic disruption from environments, leading to inaccurate planning and delayed emergency reactions. Even though reinforcement learning increases robots’ exploration speed by fusing effective guidance, the numerous interactions make the learning time-consuming and even risky (e.g., collisions). To fundamentally improve robot adaptation speed, this work seeks help from quantum power. A novel Quantum Exploration based Dreamer model (QED) was developed to facilitate reinforcement learning explorations. QED based on stochastic quantum walker quickly explores environments, evaluates action quality, and obtains a global optimal exploration strategy; then, these high-quality exploration samples will be used to facilitate reinforcement learning speed. A theoretical benefit of QED is facilitating reinforcement learning speed without changing the underlying learning architecture, which makes the proposed QED applicable to general robot learning scenarios. To validate QED effectiveness, a robot path-planning task in an obstacle-dense environment was designed. The number of needed training episodes validated the effectiveness. The results show that QED achieves around ten times faster policy learning compared with Monte Carlo tree-based reinforcement learning methods and vanilla reinforcement learning methods.

Reinforcement learning has been extensively applied to playing video games that involve visual observations, using convolutional neural networks (CNNs) to process the image input. Recent research has demonstrated that attention mechanisms in neural networks can be highly effective in various tasks, although their potential for visual reinforcement learning has not been fully explored.This study explores three approaches to incorporating attention into reinforcement learning. The first approach is to add self-attention to the later dense layers of the CNN. The second approach involves using a convolutional self-attention module within the convolutional layers of the network. The third approach incorporates self-attention with a large kernel convolution within the convolutional layers.To assess the efficacy of the proposed approaches, we conducted a comparative analysis of their performance against a baseline CNN feature extractor for a Proximal Policy Optimization (PPO) agent across multiple image-based Atari environments. Our findings suggest that attention mechanisms can be advantageous in scenarios where the PPO agent needs to adapt to minor environmental fluctuations. However, in games with fixed setups, baseline PPO tends to outperform the variations with the attention mechanism.

Cure Quest is an educational adventure game about Clinical Translational Therapeutics, the process of discovery and development of new medical treatments, drugs, devices, and therapies. The game is being developed through collaboration between faculty and students from a game design program and those from a medical school to raise awareness and improve collaboration in the “bench to bedside” process. Cure Quest aims to address this gap, first with medical students and ultimately for a general audience, with a game that instills wonder and inspires players with drug discovery challenges. In addition to the game's impact when completed, the development process itself presents a novel case study of integrating the interdisciplinary fields of game development and “team science.” We present the current version of the game in development, the unique design challenges presented by the project, and the evolution of our collaborative process.

In this paper, we explored the use of features that represent body posture and movement for automatically detecting people's emotions in non-acted standing scenarios. We focused on four emotions that are often observed when people are playing video games: triumph, frustration, defeat, and concentration. The dataset consists of recordings of the rotation angles of the player's joints while playing Wii sports games. We applied various machine learning techniques and bagged them for prediction. When body pose and movement features are used we can reach an overall accuracy of 66.5% for differentiating between these four emotions. In contrast, when using the raw joint rotations, limb rotation movement, or posture features alone, we were only able to achieve accuracy rates of 59%, 61%, and 62% respectively. Our results suggest that features representing changes in body posture can yield improved classification rates over using static postures or joint information alone.