On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures

• URL: http://arxiv.org/abs/2301.10932v3
• Date: Tue, 05 Nov 2024 14:31:28 GMT
• Title: On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures
• Authors: Xian Yu, Lei Ying,
• Abstract summary: Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes. It remains unclear if Policy Gradient (PG) methods enjoy the same global convergence guarantees as in the risk-neutral case.
• Score: 17.668631383216233
• License:
• Abstract: Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes and ensuring reliable performance in highly stochastic sequential decision-making problems. While Policy Gradient (PG) methods have been developed for risk-sensitive RL, it remains unclear if these methods enjoy the same global convergence guarantees as in the risk-neutral case \citep{mei2020global,agarwal2021theory,cen2022fast,bhandari2024global}. In this paper, we consider a class of dynamic time-consistent risk measures, named Expected Conditional Risk Measures (ECRMs), and derive PG and Natural Policy Gradient (NPG) updates for ECRMs-based RL problems. We provide global optimality {and iteration complexities} of the proposed algorithms under the following four settings: (i) PG with constrained direct parameterization, (ii) PG with softmax parameterization and log barrier regularization, (iii) NPG with softmax parameterization and entropy regularization, and (iv) approximate NPG with inexact policy evaluation. Furthermore, we test a risk-averse REINFORCE algorithm \citep{williams1992simple} and a risk-averse NPG algorithm \citep{kakade2001natural} on a stochastic Cliffwalk environment to demonstrate the efficacy of our methods and the importance of risk control.

Related papers

• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• Risk-Sensitive RL with Optimized Certainty Equivalents via Reduction to Standard RL [48.1726560631463]
  We study Risk-Sensitive Reinforcement Learning with the Optimized Certainty Equivalent (OCE) risk. We propose two general meta-algorithms via reductions to standard RL. We show that it learns the optimal risk-sensitive policy while prior algorithms provably fail.
  arXiv  Detail & Related papers  (2024-03-10T21:45:12Z)
• 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)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity [7.57543767554282]
  This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure. We derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method. We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI)
  arXiv  Detail & Related papers  (2023-06-20T15:51:25Z)
• 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)
• 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)
• A policy gradient approach for optimization of smooth risk measures [8.087699764574788]
  We consider episodic Markov decision processes, and model the risk using the broad class of smooth risk measures of the cumulative discounted reward. We propose two template policy gradient algorithms that optimize a smooth risk measure in on-policy and off-policy RL settings.
  arXiv  Detail & Related papers  (2022-02-22T17:26:28Z)
• On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk [32.97618081988295]
  We present a tight upper bound on the suboptimality of the learned policy, characterizing its dependence on the nonlinearity of the objective and the degree of risk aversion. We propose a practical implementation of PG that uses state distribution reweighting to overcome previous limitations.
  arXiv  Detail & Related papers  (2021-03-04T04:11:09Z)
• 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)

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.