Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Satheesh, Anirudh, Chen, Ziyi, Huang, Furong, Huang, Heng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
di: Satheesh, Anirudh, et al.
Pubblicazione: (2026)

Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization
di: Satheesh, Anirudh, et al.
Pubblicazione: (2026)

Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPs
di: Satheesh, Anirudh, et al.
Pubblicazione: (2025)

Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
di: Li, Mengmeng, et al.
Pubblicazione: (2023)

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
di: Gadot, Uri, et al.
Pubblicazione: (2023)

Compositional Adversarial Training for Robust Visual Watermarking
di: Satheesh, Anirudh, et al.
Pubblicazione: (2026)

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
di: Ding, Mucong, et al.
Pubblicazione: (2024)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
di: Zhong, Han, et al.
Pubblicazione: (2021)

Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
di: Wang, Shengbo, et al.
Pubblicazione: (2026)

Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs
di: Huang, Ruiquan, et al.
Pubblicazione: (2026)

Distributionally Robust Self Paced Curriculum Reinforcement Learning
di: Satheesh, Anirudh, et al.
Pubblicazione: (2025)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2024)

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
di: Chen, Ziyi, et al.
Pubblicazione: (2025)

Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
di: Li, Junyi, et al.
Pubblicazione: (2024)

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
di: Liu, Xiangyu, et al.
Pubblicazione: (2023)

Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
di: Roknilamouki, Amirhossein, et al.
Pubblicazione: (2025)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
di: Satheesh, Anirudh, et al.
Pubblicazione: (2025)

PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training
di: Satheesh, Anirudh, et al.
Pubblicazione: (2025)

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
di: Wang, Kaixin, et al.
Pubblicazione: (2023)

Efficient Algorithms for Robust Markov Decision Processes with $s$-Rectangular Ambiguity Sets
di: Ho, Chin Pang, et al.
Pubblicazione: (2026)

Last-Iterate Convergence of General Parameterized Policies in Constrained MDPs
di: Mondal, Washim Uddin, et al.
Pubblicazione: (2024)

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
di: Huang, Ruiquan, et al.
Pubblicazione: (2023)

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
di: Kitamura, Toshinori, et al.
Pubblicazione: (2025)

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

Achieve Performatively Optimal Policy for Performative Reinforcement Learning
di: Chen, Ziyi, et al.
Pubblicazione: (2025)

cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
di: Satheesh, Anirudh, et al.
Pubblicazione: (2025)

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
di: Bai, Qinbo, et al.
Pubblicazione: (2024)

Efficient Solution and Learning of Robust Factored MDPs
di: Schnitzer, Yannik, et al.
Pubblicazione: (2025)

ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
di: Turbal, Bohdan, et al.
Pubblicazione: (2026)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
di: Kash, Ian A., et al.
Pubblicazione: (2022)

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
di: Liu, Xiangyu, et al.
Pubblicazione: (2024)

Distributionally Robust Multi-Objective Optimization
di: Yang, Yufeng, et al.
Pubblicazione: (2026)

HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization
di: Huang, Feihu, et al.
Pubblicazione: (2026)

Time-Constrained Robust MDPs
di: Zouitine, Adil, et al.
Pubblicazione: (2024)

Efficient Duple Perturbation Robustness in Low-rank MDPs
di: Hu, Yang, et al.
Pubblicazione: (2024)

Provable Offline Reinforcement Learning for Structured Cyclic MDPs
di: Lee, Kyungbok, et al.
Pubblicazione: (2026)

Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation
di: Zhang, Tonghe, et al.
Pubblicazione: (2024)

Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes
di: Kumar, Navdeep, et al.
Pubblicazione: (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
VUFIND_SESSION	"5cef0c542867b646388bfb9e0a54cc03"
ui	"standard"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790731447.53 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "5cef0c542867b646388bfb9e0a54cc03" ]`]
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	"VUFIND_SESSION=5cef0c542867b646388bfb9e0a54cc03; ui=standard; language=it"
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	"216.73.216.147"
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	"7389"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2602_11387/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2602_11387/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790731447.5246
REQUEST_TIME	1790731447

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler