5 papers
Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
S. R. Eshwar, Aniruddha Mukherjee, Kintan Saha +4
In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here…
Teaching Precommitted Agents: Model-Free Policy Evaluation and Control in Quasi-Hyperbolic Discounted MDPs
S. R. Eshwar
Time-inconsistent preferences, where agents favor smaller-sooner over larger-later rewards, are a key feature of human and animal decision-making. Quasi-Hyperbolic (QH) discounting…
Monotone and Conservative Policy Iteration Beyond the Tabular Case
S. R. Eshwar, Gugan Thoppe, Ananyabrata Barua +2
We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI), variants of Policy Iteration (PI) and Conservative PI (CPI), that retain tabular guarantees under function…
Reinforcement Learning with Quasi-Hyperbolic Discounting
S. R. Eshwar, Mayank Motwani, Nibedita Roy +1
Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such framewo…
Online Learning of Weakly Coupled MDP Policies for Load Balancing and Auto Scaling
S. R. Eshwar, Lucas Lopes Felipe, Alexandre Reiffers-Masson +2
Load balancing and auto scaling are at the core of scalable, contemporary systems, addressing dynamic resource allocation and service rate adjustments in response to workload chang…