Roboschool is an open-source software for robot simulation, integrated with OpenAI Gym. It provides a variety of environments for training and testing robot controllers, including tasks familiar to Mujoco users and new challenges.
Roboschool is designed to provide a platform for training and testing robot controllers in a variety of environments. It includes twelve environments, ranging from familiar Mujoco tasks to new challenges like the Humanoid walker and multi-player Pong. The software is open-source and aims to be both interactive and robust, with trained policies available for all environments.
Orā offers daily growth exercises and guided meditations to help users develop a resilient mindset, covering areas like growth mindset, adaptability, and emotional intelligence.
The iBVP dataset is a collection of synchronized RGB and thermal infrared videos with PPG ground-truth signals acquired from an ear. It includes manual signal quality labels and dense signal-quality assessment using the SQA-PhysMD model. The dataset is designed to induce real-world variations in psycho-physiological states and head movement.
DeepSeek-R1 is a reasoning model trained via large-scale reinforcement learning (RL) without the need for supervised fine-tuning (SFT). It demonstrates remarkable performance in reasoning tasks, including self-verification and reflection. The model addresses challenges such as endless repetition and poor readability, and achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.