Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Haoran, Tang, Zeshen, Yang, Leya, Sun, Yaoru, Wang, Fang, Zhang, Siyu, Chen, Yeming
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Superpixel Semantics Representation and Pre-training for Vision-Language Task
par: Zhang, Siyu, et autres
Publié: (2023)

EchoRL: Reinforcement Learning via Rollout Echoing
par: Bi, Jinhe, et autres
Publié: (2026)

HG2P: Hippocampus-inspired High-reward Graph and Model-Free Q-Gradient Penalty for Path Planning and Motion Control
par: Wang, Haoran, et autres
Publié: (2024)

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
par: Xu, Yixuan Even, et autres
Publié: (2025)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
par: Lu, Xiaodong, et autres
Publié: (2026)

Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
par: Pang, Jing-Cheng, et autres
Publié: (2024)

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
par: Zheng, Haizhong, et autres
Publié: (2025)

ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts
par: Yu, Hang, et autres
Publié: (2025)

APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
par: Zhou, Yuzhen, et autres
Publié: (2025)

CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling
par: Qu, Zekai, et autres
Publié: (2025)

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
par: Wang, Yujie, et autres
Publié: (2026)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
par: Luo, Sijia, et autres
Publié: (2026)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
par: Liu, Bingshuai, et autres
Publié: (2025)

Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning
par: Zhang, Zhi, et autres
Publié: (2026)

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
par: Huang, Sili, et autres
Publié: (2024)

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
par: Xu, Yuhang, et autres
Publié: (2026)

SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning
par: Wan, Xu, et autres
Publié: (2025)

Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
par: Wen, Yeming, et autres
Publié: (2024)

Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
par: Ding, Zihan, et autres
Publié: (2024)

GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
par: Wang, Mianchu, et autres
Publié: (2023)

Superior Computer Chess with Model Predictive Control, Reinforcement Learning, and Rollout
par: Gundawar, Atharva, et autres
Publié: (2024)

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
par: Li, Yitong, et autres
Publié: (2026)

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
par: Heuillet, Maxime, et autres
Publié: (2025)

RTMC: Step-Level Credit Assignment via Rollout Trees
par: Wang, Tao, et autres
Publié: (2026)

Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
par: Nguyen, Hieu Trung, et autres
Publié: (2026)

Batched Low-Rank Adaptation of Foundation Models
par: Wen, Yeming, et autres
Publié: (2023)

Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
par: Cho, Minjae, et autres
Publié: (2024)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
par: Sun, Yifan, et autres
Publié: (2025)

Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation
par: Zhe, Tao, et autres
Publié: (2025)

Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative Systems
par: Hu, Liyuan
Publié: (2025)

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
par: Hao, Ce, et autres
Publié: (2023)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
par: Xu, Jiawei, et autres
Publié: (2024)

MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning
par: Kim, Youngeun
Publié: (2026)

Affordance-Guided Reinforcement Learning via Visual Prompting
par: Lee, Olivia Y., et autres
Publié: (2024)

Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE
par: Zeng, Anxiang, et autres
Publié: (2025)

Hindsight Preference Learning for Offline Preference-based Reinforcement Learning
par: Gao, Chen-Xiao, et autres
Publié: (2024)

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
par: Bae, Sangjun, et autres
Publié: (2026)

Reinforcement Learning via Value Gradient Flow
par: Xu, Haoran, et autres
Publié: (2026)

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
par: Huang, Shiting, et autres
Publié: (2026)

Innate-Values-driven Reinforcement Learning based Cooperative Multi-Agent Cognitive Modeling
par: Yang, Qin
Publié: (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
VUFIND_SESSION	"a89aff78c5eead80664bd6a336e0d0ef"
language	"fr"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790987188.462 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a89aff78c5eead80664bd6a336e0d0ef" ]`]
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=a89aff78c5eead80664bd6a336e0d0ef; language=fr; ui=standard"
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	"52630"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2309_13508/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2309_13508/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790987188.4537
REQUEST_TIME	1790987188

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler