https://github.com/facebookresearch/dcd
공식 코드Stabilizing Unsupervised Environment Design with a Learned Adversary
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.
Stabilizing Unsupervised Environment Design with a Learned Adversary
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Masked Trajectory Models for Prediction, Representation, and Control
MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control
On the model-based stochastic value gradient for continuous reinforcement learning
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Generalized Decision Transformer for Offline Hindsight Information Matching
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
Amortizing intractable inference in diffusion models for vision, language, and control
Inverse Reinforcement Learning without Reinforcement Learning
Minimax Optimal Online Imitation Learning via Replay Estimation
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
Unsupervised Learning of Object Structure and Dynamics from Videos
An empirical investigation of the challenges of real-world reinforcement learning
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.