pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

math.OC 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

On Reward-Balancing Methods for Reinforcement Learning

math.OC · 2026-04-22 · unverdicted · novelty 6.0

Reward-balancing methods normalize RL reward functions to enable greedy optimal policies, reformulated as optimal control with stochastic sampling for uncertainty and shown to improve performance in MPC simulations.

citing papers explorer

Showing 1 of 1 citing paper.

  • On Reward-Balancing Methods for Reinforcement Learning math.OC · 2026-04-22 · unverdicted · none · ref 9

    Reward-balancing methods normalize RL reward functions to enable greedy optimal policies, reformulated as optimal control with stochastic sampling for uncertainty and shown to improve performance in MPC simulations.