Papers with Code 아카이브
Multi-Armed Bandits
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 2
Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.
<span style="color:grey; opacity: 0.6">( Image credit: Microsoft Research )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/CausalML/IntrinsicallyEfficientStableOPE
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
https://github.com/CausalML/SmoothBandit
Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes
https://github.com/CoffeeddCat/Multiagent_chainMDP
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
https://github.com/MarioScappini/Bike-Sharing-Resource-Allocation-with-Combinatorial-Multi-Armed-Bandits
https://github.com/Mengyanz/Mengyanz.github.io
https://github.com/MindCode-4/code-13/tree/main/Spatial-Information-Considered-Network
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
https://github.com/MindCode-4/code-7/tree/main/gaussian_adaptive_attention
https://github.com/PlaytikaOSS/pybandits
Thompson Sampling for Contextual Bandits with Linear Payoffs
https://github.com/Ralami1859/Stochastic-Multi-Armed-Bandit
Thompson Sampling: An Asymptotically Optimal Finite Time Analysis
https://github.com/RonyAbecidan/Neural-Thompson-Sampling
https://github.com/Sirius79/acGAN
https://github.com/ThrunGroup/BanditPAM
BanditPAM: Almost Linear Time $k$-Medoids Clustering via Multi-Armed Bandits
https://github.com/UnibucProjects/DeepRLRecommenderSystem
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
https://github.com/VowpalWabbit/vowpal_wabbit
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
https://github.com/Xi-Liu/heteroscedasticbandits
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
https://github.com/YRussac/WeightedLinearBandits
https://github.com/alextanhongpin/node-bandit
A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit
https://github.com/alison-carrera/onn
A Survey of Online Experiment Design with the Stochastic Multi-Armed Bandit
https://github.com/anushalalitha5/Decentralized-Thompson-Sampling
https://github.com/backgom2357/Recommender_system_via_deep_RL
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
https://github.com/baekjin-kim/UAI2020_NonstationaryLinearBandit
Randomized Exploration for Non-Stationary Stochastic Linear Bandits
https://github.com/bahh723/model-free-rl-algos
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
https://github.com/bettyttytty/Thompson-Sampling-for-a-Fatigue-aware-Online-Recommendation-System
Thompson Sampling for a Fatigue-aware Online Recommendation System
https://github.com/bgalbraith/bandits
https://github.com/blakemas/all_epsilon
https://github.com/bremen79/parameterfree
https://github.com/c16192/Multi-Armed-Bandit
https://github.com/chicagohai/hypoeval-gen
https://github.com/ctrnh/LinearContextualBandits
https://github.com/dmolitor/pyssed
An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits
https://github.com/dsweet99/yubo
https://github.com/duanyiyao/E-TS-in-VFL
https://github.com/duanzhiihao/PyTorch_OLoptim
https://github.com/facebookresearch/Horizon
https://github.com/facebookresearch/RandomizedValueFunctions
Randomized Value Functions via Multiplicative Normalizing Flows
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.