Continuous Control
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 73
- 보존된 평가 기록
- 116
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ikostrikov/pytorch-rl
https://github.com/ikostrikov/rlpd
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
https://github.com/illidanlab/sail
Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations
https://github.com/in1t3r/ARS
Simple random search provides a competitive approach to reinforcement learning
https://github.com/inoryy/reaver
https://github.com/intelligent-environments-lab/CityLearn
Addressing Function Approximation Error in Actor-Critic Methods
https://github.com/intellisys-lab/stellaris-sc24
https://github.com/irom-princeton/dppo
https://github.com/jachiam/cpo
Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/jaem-seo/AI_tokamak_control
Addressing Function Approximation Error in Actor-Critic Methods
https://github.com/jainpankul/Augmented-Random-Search
Simple random search provides a competitive approach to reinforcement learning
https://github.com/jakegrigsby/deep_control/blob/master/deep_control/ddpg.py
https://github.com/jakegrigsby/deep_control/blob/master/deep_control/sac.py
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
https://github.com/jakegrigsby/deep_control/blob/master/deep_control/td3.py
Addressing Function Approximation Error in Actor-Critic Methods
https://github.com/jangirrishabh/Overcoming-exploration-from-demos
Overcoming Exploration in Reinforcement Learning with Demonstrations
https://github.com/jastfkjg/DDPG_Torcs_PyTorch
Simulated Car Racing Championship: Competition Software Manual
https://github.com/jcwleo/curiosity-driven-exploration-pytorch
https://github.com/jcwleo/random-network-distillation-pytorch
https://github.com/jemaw/gym-safety
Lyapunov-based Safe Policy Optimization for Continuous Control
https://github.com/jesbu1/carl
Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
https://github.com/jfpettit/flare
https://github.com/jhare96/reinforcement-learning
https://github.com/jingliang-duan/dsac-t
https://github.com/jongornet14/HyperController
https://github.com/jqueeney/geppo
Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
https://github.com/jrobine/actor-critic
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
https://github.com/jsztompka/MultiAgent-PPO
https://github.com/jsztompka/PPO-demo
https://github.com/jturner65/Getup-DartEnv
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
https://github.com/juliusfrost/Research-Paper-Implementations
https://github.com/juliusfrost/dreamer-pytorch
https://github.com/juliuskunze/cwvae-jax
https://github.com/junming-yang/mopo
https://github.com/justinjfu/diagnosing_qlearning
https://github.com/jvidals09/Decentralized-and-multi-agent-control-of-Franka-Emika-Panda-robot-in-continuous-task-execution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.