https://github.com/johannesack/offlinerlstructurednonstationarity
공식 코드Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
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.
Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning
Benchmarking Reinforcement Learning Algorithms on Real-World Robots
Autoregressive Policies for Continuous Control Deep Reinforcement Learning
Learning Shared Safety Constraints from Multi-task Demonstrations
Dream and Search to Control: Latent Space Planning for Continuous Control
Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions
Correct-by-construction reach-avoid control of partially observable linear stochastic systems
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight
Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
Sample-Efficient Imitation Learning via Generative Adversarial Nets
Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms
Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods
Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients
Structured State Space Models for In-Context Reinforcement Learning
Structured State Space Models for In-Context Reinforcement Learning
Robust Learning from Observation with Model Misspecification
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.