Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Nie, Buqing, Fu, Yangqing, Ji, Jingtian, Gao, Yue
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Select before Act: Spatially Decoupled Action Repetition for Continuous Control
von: Nie, Buqing, et al.
Veröffentlicht: (2025)

Adversarial Constrained Policy Optimization: Improving Constrained Reinforcement Learning by Adapting Budgets
von: Ma, Jianmina, et al.
Veröffentlicht: (2024)

Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
von: Zhang, Yang, et al.
Veröffentlicht: (2025)

Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?
von: Ou, Buqing, et al.
Veröffentlicht: (2026)

On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
von: Li, Haoran, et al.
Veröffentlicht: (2025)

Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
von: Zheng, Xiang, et al.
Veröffentlicht: (2023)

Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces
von: Gao, Ji, et al.
Veröffentlicht: (2026)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
von: Zhang, Tianle, et al.
Veröffentlicht: (2024)

Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
von: Li, Haoran, et al.
Veröffentlicht: (2025)

Fairness Aware Reinforcement Learning via Proximal Policy Optimization
von: La Malfa, Gabriele, et al.
Veröffentlicht: (2025)

Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
von: Liu, Qianmei, et al.
Veröffentlicht: (2024)

Extreme Value Policy Optimization for Safe Reinforcement Learning
von: Gao, Shiqing, et al.
Veröffentlicht: (2026)

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
von: Kang, Hyungkyu, et al.
Veröffentlicht: (2025)

Reinforcing Language Agents via Policy Optimization with Action Decomposition
von: Wen, Muning, et al.
Veröffentlicht: (2024)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
von: Terence, Ng Wen Zheng, et al.
Veröffentlicht: (2024)

ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning
von: Ghosh, Debamita, et al.
Veröffentlicht: (2025)

Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
von: Hazra, Somnath, et al.
Veröffentlicht: (2025)

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
von: Duan, Tianyang, et al.
Veröffentlicht: (2025)

Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
von: Gao, Gong, et al.
Veröffentlicht: (2026)

Robust Adversarial Policy Optimization Under Dynamics Uncertainty
von: Kim, Mintae, et al.
Veröffentlicht: (2026)

ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization
von: Chen, Yifei, et al.
Veröffentlicht: (2026)

Policy Optimization via Adv2: Adversarial Learning on Advantage Functions
von: Jonckheere, Matthieu, et al.
Veröffentlicht: (2023)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
von: Nguyen, Thanh, et al.
Veröffentlicht: (2024)

Adversarial Diffusion for Robust Reinforcement Learning
von: Foffano, Daniele, et al.
Veröffentlicht: (2025)

Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
von: Gupta, Nikunj, et al.
Veröffentlicht: (2026)

Doubly Optimal Policy Evaluation for Reinforcement Learning
von: Liu, Shuze Daniel, et al.
Veröffentlicht: (2024)

Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization
von: Massiani, Pierre-François, et al.
Veröffentlicht: (2025)

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
von: Zhang, Zongyuan, et al.
Veröffentlicht: (2025)

Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
von: Dawood, Murad, et al.
Veröffentlicht: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
von: Zhang, Junrui, et al.
Veröffentlicht: (2025)

Robust off-policy Reinforcement Learning via Soft Constrained Adversary
von: Nakanishi, Kosuke, et al.
Veröffentlicht: (2024)

RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
von: Zhang, Hongyin, et al.
Veröffentlicht: (2025)

Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
von: Barker, Charmaine, et al.
Veröffentlicht: (2025)

Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
von: Zhan, Simon Sinong, et al.
Veröffentlicht: (2025)

Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization
von: Dus, Mathias
Veröffentlicht: (2026)

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
von: Kong, Lingkai, et al.
Veröffentlicht: (2026)

Regularization for Adversarial Robust Learning
von: Wang, Jie, et al.
Veröffentlicht: (2024)

Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality
von: Ma, Shaocong, et al.
Veröffentlicht: (2025)

Causal-Aware Generative Adversarial Networks with Reinforcement Learning
von: Nguyen, Tu Anh Hoang, et al.
Veröffentlicht: (2025)

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?
von: Markgraf, Hannah, et al.
Veröffentlicht: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"de"
ui	"standard"
VUFIND_SESSION	"7b748eef640241ae3252b262e435649b"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790957742.811 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "7b748eef640241ae3252b262e435649b" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=de; ui=standard; VUFIND_SESSION=7b748eef640241ae3252b262e435649b"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"49901"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2507_03372/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2507_03372/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790957742.8066
REQUEST_TIME	1790957742

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler