Learning Kernel-Based MDPs from Episodic Preferential Feedback

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pavlovic, Nikola, Vakili, Sattar, Zhao, Qing
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

Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning
di: Vakili, Sattar
Pubblicazione: (2024)

A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
di: Lazzaro, Joseph, et al.
Pubblicazione: (2026)

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
di: Vakili, Sattar, et al.
Pubblicazione: (2024)

Kernelized Reinforcement Learning with Order Optimal Regret Bounds
di: Vakili, Sattar, et al.
Pubblicazione: (2023)

Differentially Private Kernelized Contextual Bandits
di: Pavlovic, Nikola, et al.
Pubblicazione: (2025)

Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
di: Kayal, Aya, et al.
Pubblicazione: (2025)

Differential Privacy in Kernelized Contextual Bandits via Random Projections
di: Pavlovic, Nikola, et al.
Pubblicazione: (2025)

Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
di: Salgia, Sudeep, et al.
Pubblicazione: (2023)

Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness
di: Pavlovic, Nikola, et al.
Pubblicazione: (2024)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
di: Ito, Shinji, et al.
Pubblicazione: (2025)

Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
di: Kayal, Aya, et al.
Pubblicazione: (2025)

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
di: Salgia, Sudeep, et al.
Pubblicazione: (2025)

Reinforcement Learning Using known Invariances
di: Cioba, Alexandru, et al.
Pubblicazione: (2025)

On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs
di: Dong, Zixuan, et al.
Pubblicazione: (2022)

No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
di: Bayrooti, Jasmine, et al.
Pubblicazione: (2025)

Reinforcement Learning from Multi-level and Episodic Human Feedback
di: Elahi, Muhammad Qasim, et al.
Pubblicazione: (2025)

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

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
di: Li, Long-Fei, et al.
Pubblicazione: (2024)

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
di: Cassel, Asaf, et al.
Pubblicazione: (2024)

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
di: Liu, Haolin, et al.
Pubblicazione: (2024)

Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
di: Rubbi, Andrea, et al.
Pubblicazione: (2026)

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

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
di: Lancewicki, Tal, et al.
Pubblicazione: (2025)

Robust Parameter Learning for Uncertain MDPs
di: Schnitzer, Yannik, et al.
Pubblicazione: (2026)

Truly No-Regret Learning in Constrained MDPs
di: Müller, Adrian, et al.
Pubblicazione: (2024)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
di: Tsuchiya, Taira, et al.
Pubblicazione: (2025)

Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization
di: Sinaga, Marshal Arijona, et al.
Pubblicazione: (2024)

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
di: Hong, Kihyuk, et al.
Pubblicazione: (2024)

Preferential Normalizing Flows
di: Mikkola, Petrus, et al.
Pubblicazione: (2024)

Learning Adversarial MDPs with Stochastic Hard Constraints
di: Stradi, Francesco Emanuele, et al.
Pubblicazione: (2024)

Nonparametric Kernel Clustering with Bandit Feedback
di: Thuot, Victor, et al.
Pubblicazione: (2026)

Local Preferential Bayesian Optimization
di: Menn, Johanna, et al.
Pubblicazione: (2026)

Principled Preferential Bayesian Optimization
di: Xu, Wenjie, et al.
Pubblicazione: (2024)

Consecutive Preferential Bayesian Optimization
di: Erarslan, Aras, et al.
Pubblicazione: (2025)

No-Regret Reinforcement Learning in Smooth MDPs
di: Maran, Davide, et al.
Pubblicazione: (2024)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
di: Schlisselberg, Ofir, et al.
Pubblicazione: (2026)

Online Episodic Convex Reinforcement Learning
di: Moreno, Bianca Marin, et al.
Pubblicazione: (2025)

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs
di: Wang, Jing, et al.
Pubblicazione: (2026)

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
di: Thoppe, Gugan, et al.
Pubblicazione: (2026)

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

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
ui	"standard"
language	"it"
VUFIND_SESSION	"3e88c2cd9bfc8f370a5e18071c5b4cfc"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790983041.335 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "3e88c2cd9bfc8f370a5e18071c5b4cfc" ]`]
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	"ui=standard; language=it; VUFIND_SESSION=3e88c2cd9bfc8f370a5e18071c5b4cfc"
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	"1217"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_23650/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_23650/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790983041.3309
REQUEST_TIME	1790983041

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler