Explicit Lipschitz Value Estimation Enhances Policy Robustness Against Perturbation

• URL: http://arxiv.org/abs/2404.13879v2
• Date: Fri, 24 May 2024 20:19:37 GMT
• Title: Explicit Lipschitz Value Estimation Enhances Policy Robustness Against Perturbation
• Authors: Xulin Chen, Ruipeng Liu, Garrett E. Katz,
• Abstract summary: In robotic control tasks, policies trained by reinforcement learning (RL) in simulation often experience a performance drop when deployed on physical hardware. We propose that Lipschitz regularization can help condition the approximated value function gradients, leading to improved robustness after training.
• Score: 2.2120851074630177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In robotic control tasks, policies trained by reinforcement learning (RL) in simulation often experience a performance drop when deployed on physical hardware, due to modeling error, measurement error, and unpredictable perturbations in the real world. Robust RL methods account for this issue by approximating a worst-case value function during training, but they can be sensitive to approximation errors in the value function and its gradient before training is complete. In this paper, we hypothesize that Lipschitz regularization can help condition the approximated value function gradients, leading to improved robustness after training. We test this hypothesis by combining Lipschitz regularization with an application of Fast Gradient Sign Method to reduce approximation errors when evaluating the value function under adversarial perturbations. Our empirical results demonstrate the benefits of this approach over prior work on a number of continuous control benchmarks.

Related papers

• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• A Case for Validation Buffer in Pessimistic Actor-Critic [1.5022206231191775]
  We show that the critic approximation error can be approximated via a fixed-point model similar to that of the Bellman value. We propose Validation Pessimism Learning (VPL) algorithm to retrieve the conditions under which the pessimistic critic is unbiased. VPL uses a small validation buffer to adjust the levels of pessimism throughout the agent training, with the pessimism set such that the approximation error of the critic targets is minimized.
  arXiv  Detail & Related papers  (2024-03-01T22:24:11Z)
• Value Gradient weighted Model-Based Reinforcement Learning [28.366157882991565]
  Model-based reinforcement learning (MBRL) is a sample efficient technique to obtain control policies. VaGraM is a novel method for value-aware model learning.
  arXiv  Detail & Related papers  (2022-04-04T13:28:31Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Offline Reinforcement Learning with Implicit Q-Learning [85.62618088890787]
  Current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy. We propose an offline RL method that never needs to evaluate actions outside of the dataset. This method enables the learned policy to improve substantially over the best behavior in the data through generalization.
  arXiv  Detail & Related papers  (2021-10-12T17:05:05Z)
• Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods [0.0]
  In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if the reinforcement signals received by the agent have a high variance, a significant underestimation bias arises. To minimize the underestimation, we introduce a parameter-free, novel deep Q-learning variant.
  arXiv  Detail & Related papers  (2021-09-22T13:49:35Z)
• Error Controlled Actor-Critic [7.936003142729818]
  On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms. We propose Error Controlled Actor-critic which ensures confining the approximation error in value function.
  arXiv  Detail & Related papers  (2021-09-06T14:51:20Z)
• Variance-Aware Off-Policy Evaluation with Linear Function Approximation [85.75516599931632]
  We study the off-policy evaluation problem in reinforcement learning with linear function approximation. We propose an algorithm, VA-OPE, which uses the estimated variance of the value function to reweight the Bellman residual in Fitted Q-Iteration.
  arXiv  Detail & Related papers  (2021-06-22T17:58:46Z)
• Robust Learning via Persistency of Excitation [4.674053902991301]
  We show that network training using gradient descent is equivalent to a dynamical system parameter estimation problem. We provide an efficient technique for estimating the corresponding Lipschitz constant using extreme value theory. Our approach also universally increases the adversarial accuracy by 0.1% to 0.3% points in various state-of-the-art adversarially trained models.
  arXiv  Detail & Related papers  (2021-06-03T18:49:05Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking [59.691919635037216]
  Policy evaluation is a key process in Reinforcement Learning (RL) We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties.
  arXiv  Detail & Related papers  (2020-02-17T13:30:43Z)

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.