Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis

arXiv:2403.08955v1 Announce Type: new
Abstract: Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face challenges in terms of iteration complexity and robustness. Risk-sensitive RL, which balances expected return and risk, has been explored for its potential to yield probabilistically robust policies, yet its iteration complexity analysis remains underexplored. In this study, we conduct a thorough iteration complexity analysis for the risk-sensitive …

abstract agents analysis applications arxiv autonomous autonomous agents challenges complexity cs.ai cs.lg enabling environments face frameworks gradient however iteration learn performance policy reinforcement reinforcement learning risk robustness terms through type