https://github.com/penglingwei/generative-actor-critic
공식 코드Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
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.
Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
AFU: Actor-Free critic Updates in off-policy RL for continuous control
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces
Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees
Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees
PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation
Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics
Decision-making and control with diffractive optical networks
Evaluating task-agnostic exploration for fixed-batch learning of arbitrary future tasks
Imitation Learning with Human Eye Gaze via Multi-Objective Prediction
Control Regularization for Reduced Variance Reinforcement Learning
Pragmatic Image Compression for Human-in-the-Loop Decision-Making
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning
Hierarchical State Abstraction Based on Structural Information Principles
RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
Benchmarking Deep Reinforcement Learning for Continuous Control
FlowPG: Action-constrained Policy Gradient with Normalizing Flows
Discovering Evolution Strategies via Meta-Black-Box Optimization
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
Discretizing Continuous Action Space for On-Policy Optimization
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
Behavior Contrastive Learning for Unsupervised Skill Discovery
Rate-Splitting for Intelligent Reflecting Surface-Aided Multiuser VR Streaming
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.