Results 91 to 100 of about 257 (142)

Two-Armed Restless Bandits with Imperfect Information: Stochastic Control and Indexability

, 2018
We present a two-armed bandit model of decision making under uncertainty where the expected return to investing in the “risky arm” increases when choosing that arm and decreases when choosing the “safe” arm.
Roland Fryer, Philipp Harms
core   +1 more source

Experimental evolutionary simulations of learning, memory and life history. [PDF]

Philos Trans R Soc Lond B Biol Sci, 2020
Morgan TJH, Suchow JW, Griffiths TL.
europepmc   +1 more source

Low-Complexity Algorithm for Restless Bandits with Imperfect Observations

We consider a class of restless bandit problems that finds a broad application area in reinforcement learning and stochastic optimization. We consider $N$ independent discrete-time Markov processes, each of which had two possible states: 1 and 0 (`good ...
Zhang, Chengzhong, Liu, Keqin, Weber, Richard   +2 more
core  

Model-based exploration is measurable across tasks but not linked to personality and psychiatric assessments. [PDF]

Sci Rep
Witte K, Thalmann M, Schulz E.
europepmc   +1 more source

Reliability of Decision-Making and Reinforcement Learning Computational Parameters

, 2021
Mkrtchian A, Valton V, Roiser JP.
europepmc   +1 more source

INDEXABILITY AND OPTIMAL INDEX POLICIES FOR A CLASS OF REINITIALISING RESTLESS BANDITS. [PDF]

Probab Eng Inf Sci, 2016
Villar SS.
europepmc   +1 more source

A foundation model to predict and capture human cognition. [PDF]

Nature
Binz M, Akata E, Bethge M, Brändle F, Callaway F, Coda-Forno J, Dayan P, Demircan C, Eckstein MK, Éltető N, Griffiths TL, Haridi S, Jagadish AK, Ji-An L, Kipnis A, Kumar S, Ludwig T, Mathony M, Mattar M, Modirshanechi A, Nath SS, Peterson JC, Rmus M, Russek EM, Saanum T, Schubert JA, Schulze Buschoff LM, Singhi N, Sui X, Thalmann M, Theis FJ, Truong V, Udandarao V, Voudouris K, Wilson R, Witte K, Wu S, Wulff DU, Xiong H, Schulz E.   +39 more
europepmc   +1 more source

Covariate-adjusted response-adaptive randomization for multi-arm clinical trials using a modified forward looking Gittins index rule. [PDF]

Biometrics, 2018
Villar SS, Rosenberger WF.
europepmc   +1 more source

Anhedonic Traits Do Not Impair Performance in a 3-Arm Bandit Task. [PDF]

Comput Psychiatr
Ramaswamy A, Yamamori Y, Vivekananda U, Litvak V, Roiser JP.   +4 more
europepmc   +1 more source

Optimal Best Arm Identification with Fixed Confidence in Restless Bandits

We study best arm identification in a restless multi-armed bandit setting with finitely many arms. The discrete-time data generated by each arm forms a homogeneous Markov chain taking values in a common, finite state space.
Karthik, P. N., Mukherjee, Arpan, Tajer, Ali, Tan, Vincent Y. F.   +3 more
core