Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning

• URL: http://arxiv.org/abs/2412.13184v1
• Date: Tue, 17 Dec 2024 18:58:00 GMT
• Title: Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning
• Authors: Chenglin Li, Guangchun Ruan, Hua Geng,
• Abstract summary: We propose a safe reinforcement learning (RL) paradigm that enables a higher level of safety without any expectation-form approximations. A tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.
• Score: 12.721239079824622
• License:
• Abstract: Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.

Related papers

• Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation [25.552241659930445]
  Key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy. Existing estimation methods rely on the infinite-horizon discounted advantage function. We propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL.
  arXiv  Detail & Related papers  (2024-12-15T10:05:23Z)
• Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning [7.888219789657414]
  In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints. We address these issues with a novel approach that begins by learning a conservatively safe policy through the use of Conditional Variational Autoencoders. We frame this as a Constrained Reward-Return Maximization problem, wherein the policy aims to optimize rewards while complying with the inferred latent safety constraints.
  arXiv  Detail & Related papers  (2024-12-11T22:00:07Z)
• Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments [63.053364805943026]
  We extend the approximate model-based shielding framework to the continuous setting. In particular we use Safety Gym as our test-bed, allowing for a more direct comparison of AMBS with popular constrained RL algorithms.
  arXiv  Detail & Related papers  (2024-02-01T17:55:08Z)
• Reward Certification for Policy Smoothed Reinforcement Learning [14.804252729195513]
  Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas. Recent studies have introduced "smoothed policies" in order to enhance its robustness. It is still challenging to establish a provable guarantee to certify the bound of its total reward.
  arXiv  Detail & Related papers  (2023-12-11T15:07:58Z)
• Probabilistic Reach-Avoid for Bayesian Neural Networks [71.67052234622781]
  We show that an optimal synthesis algorithm can provide more than a four-fold increase in the number of certifiable states. The algorithm is able to provide more than a three-fold increase in the average guaranteed reach-avoid probability.
  arXiv  Detail & Related papers  (2023-10-03T10:52:21Z)
• Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon [7.55113002732746]
  Safety, the satisfaction of state and input constraints, can be guaranteed by augmenting the learned control policy with a safety filter. Model predictive safety filters (MPSFs) are a common safety filtering approach based on model predictive control (MPC)
  arXiv  Detail & Related papers  (2023-09-20T16:35:29Z)
• A Multiplicative Value Function for Safe and Efficient Reinforcement Learning [131.96501469927733]
  We propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates constraint-free returns. We evaluate our method in four safety-focused environments, including classical RL benchmarks augmented with safety constraints and robot navigation tasks with images and raw Lidar scans as observations.
  arXiv  Detail & Related papers  (2023-03-07T18:29:15Z)
• Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks [23.907977144668838]
  We propose a partially-supervised reinforcement learning (PSRL) framework that takes advantage of an additional assumption that the true state of the POMDP is known at training time. We present the first approach for certifying safety of PSRL policies under adversarial input perturbations, and two adversarial training approaches that make direct use of PSRL.
  arXiv  Detail & Related papers  (2022-12-28T22:33:38Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
  We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-07-04T11:43:23Z)
• Penalized Proximal Policy Optimization for Safe Reinforcement Learning [68.86485583981866]
  We propose Penalized Proximal Policy Optimization (P3O), which solves the cumbersome constrained policy iteration via a single minimization of an equivalent unconstrained problem. P3O utilizes a simple-yet-effective penalty function to eliminate cost constraints and removes the trust-region constraint by the clipped surrogate objective. We show that P3O outperforms state-of-the-art algorithms with respect to both reward improvement and constraint satisfaction on a set of constrained locomotive tasks.
  arXiv  Detail & Related papers  (2022-05-24T06:15:51Z)

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.