Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence

• URL: http://arxiv.org/abs/2405.14749v1
• Date: Thu, 23 May 2024 16:16:58 GMT
• Title: Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
• Authors: Minheng Xiao, Xian Yu, Lei Ying,
• Abstract summary: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. This paper introduces a policy gradient method for risk-sensitive DRL with general coherent risk measures. We also design a categorical distributional policy gradient algorithm (CDPG) based on categorical distributional policy evaluation and trajectory gradient estimation.
• Score: 15.720824593964027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in many high-stakes applications. While most RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks to estimate the entire distribution of it. The distribution provides all necessary information about the cost and leads to a unified framework for handling various risk measures in a risk-sensitive setting. However, developing policy gradient methods for risk-sensitive DRL is inherently more complex as it pertains to finding the gradient of a probability measure. This paper introduces a policy gradient method for risk-sensitive DRL with general coherent risk measures, where we provide an analytical form of the probability measure's gradient. We further prove the local convergence of the proposed algorithm under mild smoothness assumptions. For practical use, we also design a categorical distributional policy gradient algorithm (CDPG) based on categorical distributional policy evaluation and trajectory-based gradient estimation. Through experiments on a stochastic cliff-walking environment, we illustrate the benefits of considering a risk-sensitive setting in DRL.

Related papers

• Uncertainty-aware Distributional Offline Reinforcement Learning [26.34178581703107]
  offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. We propose an uncertainty-aware distributional offline RL method to simultaneously address both uncertainty and environmentality. Our method is rigorously evaluated through comprehensive experiments in both risk-sensitive and risk-neutral benchmarks, demonstrating its superior performance.
  arXiv  Detail & Related papers  (2024-03-26T12:28:04Z)
• 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)
• 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)
• Is Risk-Sensitive Reinforcement Learning Properly Resolved? [32.42976780682353]
  We propose a novel algorithm, namely Trajectory Q-Learning (TQL), for RSRL problems with provable convergence to the optimal policy. Based on our new learning architecture, we are free to introduce a general and practical implementation for different risk measures to learn disparate risk-sensitive policies.
  arXiv  Detail & Related papers  (2023-07-02T11:47:21Z)
• Policy Evaluation in Distributional LQR [70.63903506291383]
  We provide a closed-form expression of the distribution of the random return. We show that this distribution can be approximated by a finite number of random variables. Using the approximate return distribution, we propose a zeroth-order policy gradient algorithm for risk-averse LQR.
  arXiv  Detail & Related papers  (2023-03-23T20:27:40Z)
• Risk-Sensitive Policy with Distributional Reinforcement Learning [4.523089386111081]
  This research work introduces a novel methodology based on distributional RL to derive sequential decision-making policies sensitive to the risk. Named the risk-based utility function $U$, it can be extracted from the random return distribution $Z$ naturally learnt by any distributional RL algorithm. This enables to span the complete potential trade-off between risk minimisation and expected return maximisation.
  arXiv  Detail & Related papers  (2022-12-30T14:37:28Z)
• A Risk-Sensitive Approach to Policy Optimization [21.684251937825234]
  Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. We propose a more direct approach whereby risk-sensitive objectives, specified in terms of the cumulative distribution function (CDF) of the distribution of full-episode rewards, are optimized. We demonstrate that the use of moderately "pessimistic" risk profiles, which emphasize scenarios where the agent performs poorly, leads to enhanced exploration and a continual focus on addressing deficiencies.
  arXiv  Detail & Related papers  (2022-08-19T00:55:05Z)
• 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)
• Risk Consistent Multi-Class Learning from Label Proportions [64.0125322353281]
  This study addresses a multiclass learning from label proportions (MCLLP) setting in which training instances are provided in bags. Most existing MCLLP methods impose bag-wise constraints on the prediction of instances or assign them pseudo-labels. A risk-consistent method is proposed for instance classification using the empirical risk minimization framework.
  arXiv  Detail & Related papers  (2022-03-24T03:49:04Z)

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.