https://github.com/taowang0/value-estimation-vpg
공식 코드Improving Value Estimation Critically Enhances Vanilla Policy Gradient
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.
Improving Value Estimation Critically Enhances Vanilla Policy Gradient
PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
Tactical Optimism and Pessimism for Deep Reinforcement Learning
Tactical Optimism and Pessimism for Deep Reinforcement Learning
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Action Robust Reinforcement Learning and Applications in Continuous Control
Distributional Policy Optimization: An Alternative Approach for Continuous Control
Learning Belief Representations for Imitation Learning in POMDPs
Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Direct Behavior Specification via Constrained Reinforcement Learning
SINERGYM -- A virtual testbed for building energy optimization with Reinforcement Learning
Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control
CIE: Controlling Language Model Text Generations Using Continuous Signals
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
Reduced Policy Optimization for Continuous Control with Hard Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.