Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning

• URL: http://arxiv.org/abs/2106.06931v1
• Date: Sun, 13 Jun 2021 06:28:40 GMT
• Title: Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning
• Authors: Peng Jin, Min Zhang, Jianwen Li, Li Han, Xuejun Wen
• Abstract summary: We propose an abstraction-based approach to train DRL systems on finite abstract domains. It yields neural networks whose input states are finite, making hosting DRL systems directly verifiable.
• Score: 9.428825075908131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural networks. In this paper, we propose a novel abstraction-based approach to train DRL systems on finite abstract domains instead of concrete system states. It yields neural networks whose input states are finite, making hosting DRL systems directly verifiable using model checking techniques. Our approach is orthogonal to existing DRL algorithms and off-the-shelf model checkers. We implement a resulting prototype training and verification framework and conduct extensive experiments on the state-of-the-art benchmark. The results show that the systems trained in our approach can be verified more efficiently while they retain comparable performance against those that are trained without abstraction.

Related papers

• Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study [15.949975158039452]
  In a recent study, Reinforcement Learning has been shown to outperform alternative techniques for online testing of Deep Neural Network-enabled systems. This work is a replication and extension of that empirical study. Results show that our new RL agent is able to converge to an effective policy that outperforms random testing.
  arXiv  Detail & Related papers  (2024-03-20T16:39:17Z)
• Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning [7.714620721734689]
  "Box o Flows" is an experimental control system for systematically evaluating RL algorithms in dynamic real-world scenarios. We show how state-of-the-art model-free RL algorithms can synthesize a variety of complex behaviors via simple reward specifications. We believe that the insights gained from this preliminary study and the availability of systems like the Box o Flows support the way forward for developing systematic RL algorithms.
  arXiv  Detail & Related papers  (2024-02-08T23:35:03Z)
• Efficient Deep Reinforcement Learning Requires Regulating Overfitting [91.88004732618381]
  We show that high temporal-difference (TD) error on the validation set of transitions is the main culprit that severely affects the performance of deep RL algorithms. We show that a simple online model selection method that targets the validation TD error is effective across state-based DMC and Gym tasks.
  arXiv  Detail & Related papers  (2023-04-20T17:11:05Z)
• Efficient Reinforcement Learning Through Trajectory Generation [5.766441610380447]
  A key barrier to using reinforcement learning in real-world applications is the requirement of a large number of system interactions to learn a good control policy. Off-policy and Offline RL methods have been proposed to reduce the number of interactions with the physical environment by learning control policies from historical data. We propose a trajectory generation algorithm, which adaptively generates new trajectories as if the system is being operated and explored under the updated control policies.
  arXiv  Detail & Related papers  (2022-11-30T18:49:43Z)
• Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training [14.787056022080625]
  This paper presents a novel abstraction-based approach to bypass the crux of over-approximating DNNs in reachability analysis. We extend conventional DNNs by inserting an additional abstraction layer, which abstracts a real number to an interval for training. We devise the first black-box reachability analysis approach for DNN-controlled systems, where trained DNNs are only queried as black-box oracles for the actions on abstract states.
  arXiv  Detail & Related papers  (2022-11-21T00:11:50Z)
• Implicit Offline Reinforcement Learning via Supervised Learning [83.8241505499762]
  Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. We show how implicit models can leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets.
  arXiv  Detail & Related papers  (2022-10-21T21:59:42Z)
• Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning [92.18524491615548]
  Contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL) We study how RL can be empowered by contrastive learning in a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank transitions. Under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs.
  arXiv  Detail & Related papers  (2022-07-29T17:29:08Z)
• Verifying Learning-Based Robotic Navigation Systems [61.01217374879221]
  We show how modern verification engines can be used for effective model selection. Specifically, we use verification to detect and rule out policies that may demonstrate suboptimal behavior. Our work is the first to demonstrate the use of verification backends for recognizing suboptimal DRL policies in real-world robots.
  arXiv  Detail & Related papers  (2022-05-26T17:56:43Z)
• Towards Scalable Verification of RL-Driven Systems [4.984294363450854]
  whiRL 2.0 is a tool that implements a new approach for verifying complex properties of interest for deep reinforcement learning systems. We show how our proposed techniques provide insights into the inner workings and the generalizability of DRL systems.
  arXiv  Detail & Related papers  (2021-05-25T13:34:40Z)
• Offline Reinforcement Learning from Images with Latent Space Models [60.69745540036375]
  offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions. We build on recent advances in model-based algorithms for offline RL, and extend them to high-dimensional visual observation spaces. Our approach is both tractable in practice and corresponds to maximizing a lower bound of the ELBO in the unknown POMDP.
  arXiv  Detail & Related papers  (2020-12-21T18:28:17Z)
• Information Theoretic Model Predictive Q-Learning [64.74041985237105]
  We present a novel theoretical connection between information theoretic MPC and entropy regularized RL. We develop a Q-learning algorithm that can leverage biased models.
  arXiv  Detail & Related papers  (2019-12-31T00:29:22Z)

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.