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

• URL: http://arxiv.org/abs/2403.08955v3
• Date: Sun, 06 Apr 2025 03:22:06 GMT
• Title: Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis
• Authors: Rui Liu, Anish Gupta, Erfaun Noorani, Pratap Tokekar,
• Abstract summary: Reinforcement Learning (RL) has shown exceptional performance across various applications.<n>Risk-sensitive policy gradient methods, which incorporate both expected return and risk measures, have been explored for their ability to yield more robust policies.<n>We conduct a rigorous iteration complexity analysis for the risk-sensitive policy gradient method, focusing on the REINFORCE algorithm with an exponential utility function.
• Score: 16.32678094159896
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 efficiency and robustness. Risk-sensitive policy gradient methods, which incorporate both expected return and risk measures, have been explored for their ability to yield more robust policies, yet their iteration complexity remains largely underexplored. In this work, we conduct a rigorous iteration complexity analysis for the risk-sensitive policy gradient method, focusing on the REINFORCE algorithm with an exponential utility function. We establish an iteration complexity of $\mathcal{O}(\epsilon^{-2})$ to reach an $\epsilon$-approximate first-order stationary point (FOSP). Furthermore, we investigate whether risk-sensitive algorithms can achieve better iteration complexity compared to their risk-neutral counterparts. Our analysis indicates that risk-sensitive REINFORCE can potentially converge faster. To validate our analysis, we empirically evaluate the learning performance and convergence efficiency of the risk-neutral and risk-sensitive REINFORCE algorithms in multiple environments: CartPole, MiniGrid, and Robot Navigation. Empirical results confirm that risk-averse cases can converge and stabilize faster compared to their risk-neutral counterparts. More details can be found on our website https://ruiiu.github.io/riskrl.

Related papers

• Planning and Learning in Average Risk-aware MDPs [4.696083734269232]
  We extend risk-neutral algorithms to accommodate the more general class of dynamic risk measures. Both the RVI and Q-learning algorithms are proven to converge to optimality. Our approach enables the identification of policies that are finely tuned to the intricate risk-awareness of the agent that they serve.
  arXiv  Detail & Related papers  (2025-03-22T03:18:09Z)
• Risk-Averse Certification of Bayesian Neural Networks [70.44969603471903]
  We propose a Risk-Averse Certification framework for Bayesian neural networks called RAC-BNN. Our method leverages sampling and optimisation to compute a sound approximation of the output set of a BNN. We validate RAC-BNN on a range of regression and classification benchmarks and compare its performance with a state-of-the-art method.
  arXiv  Detail & Related papers  (2024-11-29T14:22:51Z)
• SOREL: A Stochastic Algorithm for Spectral Risks Minimization [1.6574413179773761]
  spectral risk has wide applications in machine learning, especially in real-world decision-making. By assigning different weights to the losses of different sample points, it allows the model's performance to lie between the average performance and the worst-case performance. We propose SOREL, the first gradient-based algorithm with convergence guarantees for the spectral risk minimization.
  arXiv  Detail & Related papers  (2024-07-19T18:20:53Z)
• Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning [19.292214425524303]
  We study risk-sensitive reinforcement learning (RL), a crucial field due to its ability to enhance decision-making in scenarios where it is essential to manage uncertainty and minimize potential adverse outcomes. Our work focuses on applying the entropic risk measure to RL problems. We center on the linear Markov Decision Process (MDP) setting, a well-regarded theoretical framework that has yet to be examined from a risk-sensitive standpoint.
  arXiv  Detail & Related papers  (2024-07-10T13:09:52Z)
• Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation [54.61816424792866]
  We introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. We design two innovative meta-algorithms: textttRS-DisRL-M, a model-based strategy for model-based function approximation, and textttRS-DisRL-V, a model-free approach for general value function approximation.
  arXiv  Detail & Related papers  (2024-02-28T08:43:18Z)
• Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts [11.765000124617186]
  We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage optimization problems. We show that our algorithm is superior to risk-neutral Soft Actor-Critic as well as to two benchmark approaches for robust deep reinforcement learning.
  arXiv  Detail & Related papers  (2024-02-15T14:55:38Z)
• Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback [57.6775169085215]
  Risk-sensitive reinforcement learning aims to optimize policies that balance the expected reward and risk. We present a novel framework that employs an Iterated Conditional Value-at-Risk (CVaR) objective under both linear and general function approximations. We propose provably sample-efficient algorithms for this Iterated CVaR RL and provide rigorous theoretical analysis.
  arXiv  Detail & Related papers  (2023-07-06T08:14:54Z)
• Near-optimal Policy Identification in Active Reinforcement Learning [84.27592560211909]
  AE-LSVI is a novel variant of the kernelized least-squares value RL (LSVI) algorithm that combines optimism with pessimism for active exploration. We show that AE-LSVI outperforms other algorithms in a variety of environments when robustness to the initial state is required.
  arXiv  Detail & Related papers  (2022-12-19T14:46:57Z)
• Optimal Algorithms for Stochastic Complementary Composite Minimization [55.26935605535377]
  Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization. We provide novel excess risk bounds, both in expectation and with high probability. Our algorithms are nearly optimal, which we prove via novel lower complexity bounds for this class of problems.
  arXiv  Detail & Related papers  (2022-11-03T12:40:24Z)
• RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk [28.811725782388688]
  We propose and analyze a new framework to jointly model the risk associated with uncertainties in finite-horizon and discounted infinite-horizon MDPs. We show that when the risk-aversion is defined using either EVaR or the entropic risk, the optimal policy in RASR can be computed efficiently using a new dynamic program formulation with a time-dependent risk level.
  arXiv  Detail & Related papers  (2022-09-09T00:34:58Z)
• Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning [0.0]
  We develop an efficient approach to estimate a class of dynamic spectral risk measures with deep neural networks. We also develop a risk-sensitive actor-critic algorithm that uses full episodes and does not require any additional nested transitions.
  arXiv  Detail & Related papers  (2022-06-29T14:11:15Z)
• Efficient Risk-Averse Reinforcement Learning [79.61412643761034]
  In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. We prove that under certain conditions this inevitably leads to a local-optimum barrier, and propose a soft risk mechanism to bypass it. We demonstrate improved risk aversion in maze navigation, autonomous driving, and resource allocation benchmarks.
  arXiv  Detail & Related papers  (2022-05-10T19:40:52Z)
• TOPS: Transition-based VOlatility-controlled Policy Search and its Global Convergence [9.607937067646617]
  This paper proposes Transition-based VOlatility-controlled Policy Search (TOPS) It is a novel algorithm that solves risk-averse problems by learning from (possibly non-consecutive) transitions instead of only consecutive trajectories. Both theoretical analysis and experimental results demonstrate a state-of-the-art level of risk-averse policy search methods.
  arXiv  Detail & Related papers  (2022-01-24T18:29:23Z)
• A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits [91.3755431537592]
  This paper unifies the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem. Using the contraction principle in the theory of large deviations, we prove novel concentration bounds for continuous risk functionals. We show that a wide class of risk functionals as well as "nice" functions of them satisfy the continuity condition.
  arXiv  Detail & Related papers  (2021-08-25T17:09:01Z)
• Learning Sampling Policy for Faster Derivative Free Optimization [100.27518340593284]
  We propose a new reinforcement learning based ZO algorithm (ZO-RL) with learning the sampling policy for generating the perturbations in ZO optimization instead of using random sampling. Our results show that our ZO-RL algorithm can effectively reduce the variances of ZO gradient by learning a sampling policy, and converge faster than existing ZO algorithms in different scenarios.
  arXiv  Detail & Related papers  (2021-04-09T14:50:59Z)
• Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning [36.015585972493575]
  This paper considers batch Reinforcement Learning (RL) with general value function approximation. The excess risk of Empirical Risk Minimizer (ERM) is bounded by the Rademacher complexity of the function class. Fast statistical rates can be achieved by using tools of local Rademacher complexity.
  arXiv  Detail & Related papers  (2021-03-25T14:45:29Z)
• Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation [48.744735294559824]
  Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts. In this paper, we propose a new algorithm, COPOE, that overcomes the sample complexity issue of PCPG while retaining its robustness to model misspecification. The result is an improvement in sample complexity from $widetildeO (1/epsilon11)$ for PCPG to $widetildeO (1/epsilon3)$ for PCPG, nearly bridging the gap with value-based techniques.
  arXiv  Detail & Related papers  (2021-03-24T01:42:59Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)
• A Full Characterization of Excess Risk via Empirical Risk Landscape [8.797852602680445]
  In this paper, we provide a unified analysis of the risk of the model trained by a proper algorithm with both smooth convex and non- loss functions.
  arXiv  Detail & Related papers  (2020-12-04T08:24:50Z)
• Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity [58.70807593332932]
  We study oracle complexity of gradient based methods for approximation problems. We focus on instance-dependent complexity instead of worst case complexity. Our proposed algorithm and its analysis provide a theoretical justification for the success of moment estimation.
  arXiv  Detail & Related papers  (2020-06-08T09:25:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.