Results 11 to 20 of about 2,925,819 (300)
Correction: Enhanced Thompson sampling by roulette wheel selection for screening ultralarge combinatorial libraries [PDF]
Journal of CheminformaticsHongtao Zhao +5 more
doaj +2 more sources
CoRR, 2021 Proceedings of the 38th International Conference on Machine ...
Branislav Kveton +6 more
openaire +3 more sources
CoRR, 2021 We introduce a novel anytime Batched Thompson sampling policy for multi-armed bandits where the agent observes the rewards of her actions and adjusts her policy only at the end of a small number of batches. We show that this policy simultaneously achieves a problem dependent regret of order $O(\log(T))$ and a minimax regret of order $O(\sqrt{T\log(T)})$
Cem Kalkanli, Ayfer Özgür
openaire +4 more sources
Parallelizing Thompson Sampling
CoRR, 2021 How can we make use of information parallelism in online decision making problems while efficiently balancing the exploration-exploitation trade-off? In this paper, we introduce a batch Thompson Sampling framework for two canonical online decision making problems, namely, stochastic multi-arm bandit and linear contextual bandit with finitely many arms.
Amin Karbasi +2 more
openaire +3 more sources
Regenerative Particle Thompson Sampling
CoRR, 2022 Mainbody 14 pages, appendix 32 pages, 16 ...
Zeyu Zhou +3 more
openaire +3 more sources
CoRR, 2020 Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation.
Weitong Zhang +3 more
openaire +3 more sources
Thompson Sampling with a Mixture Prior
CoRR, 2021 We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a learning agent faces different classes of problems. We incorporate this structure in a natural way by initializing TS with a mixture prior, and call the resulting algorithm ...
Joey Hong +4 more
openaire +4 more sources
Ensemble Bootstrapped Deep Deterministic Policy Gradient for Vision-Based Robotic Grasping
IEEE Access, 2021 With sufficient practice, humans can grab objects they have never seen before through brain decision-making. However, the manipulators, which has a wide range of applications in industrial production, can still only grab specific objects. Because most of
Weiwei Liu +6 more
doaj +1 more source
On Thompson Sampling and Asymptotic Optimality [PDF]
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017 We discuss some recent results on Thompson sampling for nonparametric reinforcement learning in countable classes of general stochastic environments. These environments can be non-Markovian, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its value converges in ...
Jan Leike +3 more
openaire +2 more sources
CoRR, 2020 We study a cooperative multi-agent multi-armed bandits with M agents and K arms. The goal of the agents is to minimized the cumulative regret. We adapt a traditional Thompson Sampling algoirthm under the distributed setting. However, with agent's ability to communicate, we note that communication may further reduce the upper bound of the regret for a ...
Dong, Jing +3 more
openaire +3 more sources