태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.
Source: Randomized Value Functions via Multiplicative Normalizing Flows
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The Replica Dataset is a dataset of high quality reconstructions of a variety of indoor spaces. Each reconstruction has clean dense geometry, high resolution and high dynamic range textures, glass and mirror surface information, planar segmentation as well as semantic class and instance segmentation. Source: The Replica Dataset: A Digital Replica of Indoor Spaces
A rich, extensible and efficient environment that contains 45,622 human-designed 3D scenes of visually realistic houses, ranging from single-room studios to multi-storied houses, equipped with a diverse set of fully labeled 3D objects, textures and scene layouts, based on the SUNCG dataset (Song et.al.) Source: Building Generalizable Agents with a Realistic and Rich 3D Environment
This Quantum Dots Stability Diagrams (QDSD) Dataset aggregates experimental stability diagrams of quantum dots from different research groups. Only the interpolated_csv.zip and labels.json files are necessary for offline tuning or machine-learning tasks. Currently, only single-dot stability diagrams are labelled. The original data have been provided by different research groups based on the following references: Rochette et al. 2019 Gaudreau et al. 2009 Stuyck et al. 2021 See the README.md for files description
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.