ARXIV:2603.22169 · ROBOTICS PLANNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Dmitrii Plotnikov · Iaroslav Kolomiets · Dmitrii Maliukov · Dmitrij Kosenkov · Daniia Zinniatullina · Artem Trandofilov · +7 at arXiv

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Blocked on Code›Score7.0Evidence unverified

Opportunity summary

Pain A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction…

METHOD

Full abstract

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment. In our framework, executable Behavior Trees are repeatedly refined by a Large Language Model actor using structured natural-language feedback produced by a Vision-Language Model critic that observes the physical robot and execution traces. Unlike conventional reinforcement learning, policy updates in VRL occur directly at the symbolic planning level, without gradient-based optimization. This enables transparent reasoning, explicit causal feedback, and human-interpretable policy evolution. We validate the proposed framework on a real mobile robot performing a multi-stage manipulation and navigation task under execution uncertainty. Experimental results show that the framework supports explainable policy improvements, closed-loop adaptation to execution failures, and reliable deployment on physical robotic systems.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment.

WHY NOW

Robotics Planning moved forward this cycle; last verified April 2026. Public score 7.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainA closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Evidence0 refs | 0 sources | 17% coverage

Blockerno shell-level blocker reported

Analysis summary

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

ARXIV:2603.22169 · ROBOTICS PLANNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Dmitrii Plotnikov · Iaroslav Kolomiets · Dmitrii Maliukov · Dmitrij Kosenkov · Daniia Zinniatullina · Artem Trandofilov · +7 at arXiv

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Blocked on Code›Score7.0Evidence unverified

Opportunity summary

Pain A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Robotics Planning moved forward this cycle; last verified April 2026. Public score 7.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainA closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Evidence0 refs | 0 sources | 17% coverage

Blockerno shell-level blocker reported

Analysis summary

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.22169

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback27 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

7.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Robotics Planning moved forward this cycle; last verified April 2026. Public score 7.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 7.0/10 on the public viability pass. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Robotics Planning moved forward this cycle; last verified April 2026. Public score 7.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Robotics Planning

Competitors

not indexed

Competitive landscape

A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.

Segment

Robotics Planning

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.22169 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(27)

Decision-Making for Path Planning of Mobile Robots Under Uncertainty: A Review of Belief-Space Planning Simplifications

2025V. Malathi, Pramod Sreedharan et al.

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences

2025Anukriti Singh, Amisha Bhaskar et al.

Vision-language model-driven scene understanding and robotic object manipulation

2024Sichao Liu, Jianjing Zhang et al.

Affordance-Guided Reinforcement Learning via Visual Prompting

2024Olivia Y. Lee, Annie Xie et al.

Learning Reward for Robot Skills Using Large Language Models via Self-Alignment

2024Yuwei Zeng, Yao Mu et al.

BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs

2024Riccardo Andrea Izzo, Gianluca Bardaro et al.

AutoGPT+P: Affordance-based Task Planning with Large Language Models

2024Timo Birr, Christoph Pohl et al.

"Task Success" is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors

2024L. Guan, Yifan Zhou et al.

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback

2024Yufei Wang, Zhanyi Sun et al.

Large Language Models for Robotics: Opportunities, Challenges, and Perspectives

2024Jiaqi Wang, Zihao Wu et al.

LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems

2023Artem Lykov, Maria Dronova et al.

CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations

2023Xuzhe Dang, Stefan Edelkamp et al.

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

2023Juan Rocamonde, Victoriano Montesinos et al.

ProgPrompt: program generation for situated robot task planning using large language models

2023Ishika Singh, Valts Blukis et al.

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

2023Wenlong Huang, Chen Wang et al.

Voyager: An Open-Ended Embodied Agent with Large Language Models

2023Guanzhi Wang, Yuqi Xie et al.

Self-Refine: Iterative Refinement with Self-Feedback

2023Aman Madaan, Niket Tandon et al.

Reflexion: language agents with verbal reinforcement learning

2023Noah Shinn, Federico Cassano et al.

Task and Motion Planning with Large Language Models for Object Rearrangement

2023Yan Ding, Xiaohan Zhang et al.

ReAct: Synergizing Reasoning and Acting in Language Models

2022Shunyu Yao, Jeffrey Zhao et al.

Showing 20 of 27 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkLarge Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

7.0

Prior WorkOpen-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA

7.0

Prior WorkRoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

7.0

Prior WorkJump-Start Reinforcement Learning with Vision-Language-Action Regularization

7.0

Prior WorkAtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

7.0

Prior WorkAPPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model

7.0

Extension

Builds On ThisVORL-EXPLORE: A Hybrid Learning Planning Approach to Multi-Robot Exploration in Dynamic Environments

3.0

Builds On ThisSelf-Correcting VLA: Online Action Refinement via Sparse World Imagination

6.0

Commercially relevant

Higher ViabilityDreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models

8.0

Higher ViabilitySVLL: Staged Vision-Language Learning for Physically Grounded Embodied Task Planning

8.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.22169
Route: /paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning
Active tab: read
Artifact: closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning/paper-pack
REST build passport API/api/v1/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "fc8155a2-d9ec-48e1-b518-4c6c963d7a33",
  "arxiv_id": "2603.22169",
  "canonical_route": "/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
  "endpoints": {
    "paper_pack": "/api/v1/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning/paper-pack",
    "build_passport": "/api/v1/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Canonical ID closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning | Route /paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.22169"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning",
  "normalized_query": "2603.22169",
  "route": "/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
  "paper_ref": "closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

/buildability/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

Watchwatch

Subject: Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

Paper ref

closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning

arXiv id

2603.22169

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

ab3f86ca22a986a43d10aebebffed8b932ad34d35c0d6413c884a29c1cbddd68

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning#webpage",
      "url": "https://sciencetostartup.com/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
      "name": "Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning",
      "description": "A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning#scholarlyArticle",
      "headline": "Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning",
      "description": "A closed-loop verbal reinforcement learning framework for interpretable and adaptive task-level robotic planning, leveraging LLMs and VLM for symbolic policy refinement.",
      "url": "https://sciencetostartup.com/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning",
      "sameAs": "https://arxiv.org/abs/2603.22169",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.22169"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-23T16:28:36.000Z",
      "author": [
        {
          "@type": "Person",
          "name": "Dmitrii Plotnikov"
        },
        {
          "@type": "Person",
          "name": "Iaroslav Kolomiets"
        },
        {
          "@type": "Person",
          "name": "Dmitrii Maliukov"
        },
        {
          "@type": "Person",
          "name": "Dmitrij Kosenkov"
        },
        {
          "@type": "Person",
          "name": "Daniia Zinniatullina"
        },
        {
          "@type": "Person",
          "name": "Artem Trandofilov"
        },
        {
          "@type": "Person",
          "name": "Georgii Gazaryan"
        },
        {
          "@type": "Person",
          "name": "Kirill Bogatikov"
        },
        {
          "@type": "Person",
          "name": "Timofei Kozlov"
        },
        {
          "@type": "Person",
          "name": "Igor Duchinskii"
        },
        {
          "@type": "Person",
          "name": "Mikhail Konenkov"
        },
        {
          "@type": "Person",
          "name": "Miguel Altamirano Cabrera"
        },
        {
          "@type": "Person",
          "name": "Dzmitry Tsetserukou"
        }
      ],
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c8435d1253636d1865f78de58e2ac37260f0aaf9"
          },
          "url": "https://www.semanticscholar.org/paper/c8435d1253636d1865f78de58e2ac37260f0aaf9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "eafd292ee60cc833eee3a02c943e509f9ec46221"
          },
          "url": "https://www.semanticscholar.org/paper/eafd292ee60cc833eee3a02c943e509f9ec46221"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4dc8cca917765a48b4942009dc04da68bb2370f3"
          },
          "url": "https://www.semanticscholar.org/paper/4dc8cca917765a48b4942009dc04da68bb2370f3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "df9b2b471b9b2550a29b2fd2df6b9d5967f9133f"
          },
          "url": "https://www.semanticscholar.org/paper/df9b2b471b9b2550a29b2fd2df6b9d5967f9133f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "83331243fcaeab4d5c02145d62f3d42df2c2d651"
          },
          "url": "https://www.semanticscholar.org/paper/83331243fcaeab4d5c02145d62f3d42df2c2d651"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ea9255d308852ed1f2f2ba5469a0b2df294f6aa1"
          },
          "url": "https://www.semanticscholar.org/paper/ea9255d308852ed1f2f2ba5469a0b2df294f6aa1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ec783473ce69f5a92104587aec23189206096e6c"
          },
          "url": "https://www.semanticscholar.org/paper/ec783473ce69f5a92104587aec23189206096e6c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4c98e18cf16395b95ffaaeeac3eceffa608dcf8d"
          },
          "url": "https://www.semanticscholar.org/paper/4c98e18cf16395b95ffaaeeac3eceffa608dcf8d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "550006bea81e4ccb67743dd1b82a70b86b48d93a"
          },
          "url": "https://www.semanticscholar.org/paper/550006bea81e4ccb67743dd1b82a70b86b48d93a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8296eef3797afd1515021ff568a694412c38101b"
          },
          "url": "https://www.semanticscholar.org/paper/8296eef3797afd1515021ff568a694412c38101b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "98035acf98e823c07138aea711d02db76b663d38"
          },
          "url": "https://www.semanticscholar.org/paper/98035acf98e823c07138aea711d02db76b663d38"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9a251558d87cf30c15f0734c2cbac1d253fa41a7"
          },
          "url": "https://www.semanticscholar.org/paper/9a251558d87cf30c15f0734c2cbac1d253fa41a7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fb09b581589e1195ff018179c6a11668587c6d64"
          },
          "url": "https://www.semanticscholar.org/paper/fb09b581589e1195ff018179c6a11668587c6d64"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "24d836bbc35413d76c3c69cb30bfc0f1449f5207"
          },
          "url": "https://www.semanticscholar.org/paper/24d836bbc35413d76c3c69cb30bfc0f1449f5207"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1cd8373490efc2d74c2796f4b2aa27c7d4415ec9"
          },
          "url": "https://www.semanticscholar.org/paper/1cd8373490efc2d74c2796f4b2aa27c7d4415ec9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f197bf0fc2f228483f6af3285000d54d8d97f9eb"
          },
          "url": "https://www.semanticscholar.org/paper/f197bf0fc2f228483f6af3285000d54d8d97f9eb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3aaf6a2cbad5850ad81ab5c163599cb3d523436f"
          },
          "url": "https://www.semanticscholar.org/paper/3aaf6a2cbad5850ad81ab5c163599cb3d523436f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0671fd553dd670a4e820553a974bc48040ba0819"
          },
          "url": "https://www.semanticscholar.org/paper/0671fd553dd670a4e820553a974bc48040ba0819"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e4be613cc875e61b8c1c6c60d958f1c20d12d6c0"
          },
          "url": "https://www.semanticscholar.org/paper/e4be613cc875e61b8c1c6c60d958f1c20d12d6c0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "99832586d55f540f603637e458a292406a0ed75d"
          },
          "url": "https://www.semanticscholar.org/paper/99832586d55f540f603637e458a292406a0ed75d"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 7
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Robotics Planning"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Robotics Planning",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Closed-Loop Verbal Reinforcement Learning for Task-Level Rob",
          "item": "https://sciencetostartup.com/paper/closed-loop-verbal-reinforcement-learning-for-task-level-robotic-planning"
        }
      ]
    }
  ]
}

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(27)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(27)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline