https://github.com/panxulab/lsvi-ase
공식 코드More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Papers with Code 아카이브
Thompson Sampling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Thompson sampling, named after William R. Thompson, is a heuristic for choosing actions that addresses the exploration-exploitation dilemma in the multi-armed bandit problem. It consists of choosing the action that maximizes the expected reward with respect to a randomly drawn belief.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/quan-zhou/mab
공식 코드Representative Action Selection for Large Action-Space Meta-Bandits
https://github.com/rahbararman/cost-efficient-odm
공식 코드Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach
https://github.com/raihan-seraj/tsetlin-machine-for-solving-contextual-bandit-problems
공식 코드https://github.com/raminaghods/NATS
공식 코드Multi-Agent Active Search using Realistic Depth-Aware Noise Model
https://github.com/raymzhang/cts-mismatched-paradox
공식 코드Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
https://github.com/rgautron/DssatBanditEnv
공식 코드Optimal Thompson Sampling strategies for support-aware CVaR bandits
https://github.com/rinuboney/l2p-pommerman
공식 코드Learning to Play Imperfect-Information Games by Imitating an Oracle Planner
https://github.com/sabzer/distributed-bo
공식 코드Distributed Thompson sampling under constrained communication
https://github.com/saeedghoorchian/d-lints-rp
공식 코드Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems
https://github.com/sail-sg/oat
공식 코드https://github.com/shidani/rankingcontextualbandits
공식 코드https://github.com/shiralab/opts
공식 코드Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers
https://github.com/sinanyildirim/smc_dp_adatr
공식 코드Differentially Private Online Bayesian Estimation With Adaptive Truncation
https://github.com/skezle/BADAM
공식 코드Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods
https://github.com/skywalker6174/3d-isometry-robust
공식 코드On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks
https://github.com/stanfordai4hi/adaptive-interventions-with-goals
공식 코드Adaptive Interventions with User-Defined Goals for Health Behavior Change
https://github.com/sulgik/orts
공식 코드Odds-Ratio Thompson Sampling to Control for Time-Varying Effect
https://github.com/szrlee/GPT-HyperAgent
공식 코드https://github.com/szrlee/ensemble_plus_plus
공식 코드https://github.com/thomyphan/anytime-mapf
공식 코드Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search
https://github.com/thomyphan/planning
공식 코드Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling
https://github.com/timo-verstraeten/spts-experiments
공식 코드Scalable Optimization for Wind Farm Control using Coordination Graphs
https://github.com/uquh/tsroots
공식 코드Optimizing Posterior Samples for Bayesian Optimization via Rootfinding
https://github.com/vaswanis/randucb
공식 코드Old Dog Learns New Tricks: Randomized UCB for Bandit Problems
https://github.com/vidits-kth/LinConTS
공식 코드https://github.com/vub-ai-lab/bdpi
공식 코드Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
https://github.com/wesselb/NeuralProcesses.jl
공식 코드Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
https://github.com/xiwenchao/conTS-TOIS-2021
공식 코드Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users
https://github.com/yhjung88/ThompsonSamplinginRestlessBandits
공식 코드Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems
https://github.com/yunzhe-zhou/PBL
공식 코드Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach
https://github.com/yusonghust/HierarchicyBandit
공식 코드https://github.com/zhiwang123/eps-mpmab-ts
공식 코드https://github.com/zihaophys/topk_colt23
공식 코드https://github.com/BBloggsbott/k-armed-bandits
https://github.com/CoffeeddCat/Multiagent_chainMDP
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.