TA4a.3

Bimodal Bandits: Max-Mean Regret Minimization

Adit Jain, Cornell University, United States; Sujay Bhatt, JP Morgan Chase and Co., United States; Vikram Krishnamurthy, Cornell University, United States; Alec Koppel, JP Morgan Chase and Co., United States
Session:
TA4a: Safe Reinforcement Learning Lecture
Track:
Adaptive Systems, Machine Learning, and Data Analytics
Location:
Nautilus
Presentation Time:
Tue, 29 Oct, 09:05 - 09:30 PT (UTC -7)
Presentation
Discussion
Resources
No resources available.
Session TA4a
TA4a.1: Tensor low-rank approximation of value functions in multi-task RL
Sergio Rozada, King Juan Carlos University, Spain; Santiago Paternain, Rensselaer Polytechnic Institute, United States; Juan Andrés Bazarque, University of Pittsburgh, United States; Antonio G. Marques, King Juan Carlos University, Spain
TA4a.2: Asynchronous best-response for learning Nash in constrained Markov games with an α-potential
Soham Das, Ceyhun Eksin, Texas A&M University, United States
TA4a.3: Bimodal Bandits: Max-Mean Regret Minimization
Adit Jain, Cornell University, United States; Sujay Bhatt, JP Morgan Chase and Co., United States; Vikram Krishnamurthy, Cornell University, United States; Alec Koppel, JP Morgan Chase and Co., United States
Contacts