https://github.com/data-science-in-mechanical-engineering/hci-gibo
Simple random search provides a competitive approach to reinforcement learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Continuous control in the context of playing games, especially within artificial intelligence (AI) and machine learning (ML), refers to the ability to make a series of smooth, ongoing adjustments or actions to control a game or a simulation. This is in contrast to discrete control, where the actions are limited to a set of specific, distinct choices. Continuous control is crucial in environments where precision, timing, and the magnitude of actions matter, such as driving a car in a racing game, controlling a character in a simulation, or managing the flight of an aircraft in a flight simulator.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Simple random search provides a competitive approach to reinforcement learning
Learning State Abstractions for Transfer in Continuous Control
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
On-Policy Trust Region Policy Optimisation with Replay Buffers
Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse
High-Dimensional Continuous Control Using Generalized Advantage Estimation
Benchmarking Reinforcement Learning Algorithms on Real-World Robots
Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
Online and Offline Reinforcement Learning by Planning with a Learned Model
Simple random search provides a competitive approach to reinforcement learning
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.