ARXIV:2602.12125 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

arXiv

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance. In this work, we first theoretically show that OPD is a special case of dense…

METHOD

Full abstract

On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy distillation and reinforcement learning (RL) paradigms. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model. Then, we propose the Generalized On-Policy Distillation (G-OPD) framework, which extends the standard OPD objective by introducing a flexible reference model and a reward scaling factor that controls the relative weight of the reward term against the KL regularization. Through comprehensive experiments on math reasoning and code generation tasks, we derive two novel insights: (1) Setting the reward scaling factor to be greater than 1 (i.e., reward extrapolation), which we term ExOPD, consistently improves over standard OPD across a range of teacher-student size pairings. In particular, in the setting where we merge the knowledge from different domain experts, obtained by applying domain-specific RL to the same student model, back into the original student, ExOPD enables the student to even surpass the teacher's performance boundary and outperform the domain teachers. (2) Building on ExOPD, we further find that in the strong-to-weak distillation setting (i.e., distilling a smaller student from a larger teacher), performing reward correction by choosing the reference model as the teacher's base model before RL yields a more accurate reward signal and further improves distillation performance. However, this choice assumes access to the teacher's pre-RL variant and incurs more computational overhead. We hope our work offers new insights for future research on OPD.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL…

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

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

Opportunity summary

Score5.0

PainDevelop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2602.12125 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

arXiv

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

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

Opportunity summary

Score5.0

PainDevelop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2602.12125

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

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 fallback36 indexednot indexed

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

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy distillation and reinforcement learning (RL) paradigms. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.
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

Reinforcement Learning

Competitors

not indexed

Competitive landscape

Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.

Segment

Reinforcement Learning

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.12125 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(36)

Reinforcement Learning via Self-Distillation

2026Jonas Hubotter, Frederike Lubeck et al.

Self-Distillation Enables Continual Learning

2026Idan Shenfeld, Mehul Damani et al.

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

2026Siyan Zhao, Zhihui Xie et al.

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning

2026Kun Liang, Clive Bai et al.

MiMo-V2-Flash Technical Report

2026Xiaomi LLM-Core Team Bangjun Xiao, Bing Xia et al.

Black-Box On-Policy Distillation of Large Language Models

2025Tianzhu Ye, Li Dong et al.

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

2025Wenkai Yang, Weijie Liu et al.

Agentic Reinforcement Learning with Implicit Step Rewards

2025Xiaoqian Liu, Ke Wang et al.

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

2025Chris Liu, Liang Zeng et al.

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning

2025Yiju Guo, Wenkai Yang et al.

OpenThoughts: Data Recipes for Reasoning Models

2025E. Guha, Ryan Marten et al.

MathArena: Evaluating LLMs on Uncontaminated Math Competitions

2025Mislav Balunovi'c, Jasper Dekoninck et al.

Qwen3 Technical Report

2025An Yang, Anfeng Li et al.

DeepCritic: Deliberate Critique with Large Language Models

2025Wenkai Yang, Jingwen Chen et al.

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

2025Zhiwei He, Tian Liang et al.

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

2025Jingcheng Hu, Yinmin Zhang et al.

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning

2025Wenkai Yang, Shuming Ma et al.

LIMO: Less is More for Reasoning

2025Yixin Ye, Zhen Huang et al.

Process Reinforcement through Implicit Rewards

2025Ganqu Cui, Lifan Yuan et al.

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2025Adam Suma, Samuel Dauncey

Showing 20 of 36 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 WorkReinforcement-aware Knowledge Distillation for LLM Reasoning

5.0

Extension

Builds On ThisA Survey of On-Policy Distillation for Large Language Models

2.0

Builds On ThisOPRD: On-Policy Representation Distillation

0.0

Builds On ThisThe Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

3.0

Builds On ThisRevisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

4.0

Builds On ThisOn the Geometry of On-Policy Distillation

0.0

Commercially relevant

Higher ViabilityKL for a KL: On-Policy Distillation with Control Variate Baseline

7.0

Higher ViabilityRethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

7.0

Higher ViabilityPrune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning

7.0

Higher ViabilityTeacher-Guided Policy Optimization for LLM Distillation

7.0

Conflicting

none indexed

Related Resources

Just-In-Time Reinforcement Learning(glossary)
Multi-Agent Reinforcement Learning(glossary)
Multi-Agent Test-Time Reinforcement Learning (MATTRL)(glossary)
How does PRISM improve reinforcement learning?(question)
What is the significance of reinforcement learning in AI?(question)
How does RetroAgent improve reinforcement learning?(question)
Reinforcement Learning – Use Cases(use_case)

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: 2602.12125
Route: /paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation
Active tab: read
Artifact: learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation/paper-pack
REST build passport API/api/v1/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation/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": "ab69ef61-b829-4f3e-8edc-ac4954701fcf",
  "arxiv_id": "2602.12125",
  "canonical_route": "/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation/paper-pack",
    "build_passport": "/api/v1/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation/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/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
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

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Canonical ID learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation | Route /paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.12125"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation",
  "normalized_query": "2602.12125",
  "route": "/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
  "paper_ref": "learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
  "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: Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

/buildability/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

Watchwatch

Subject: Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

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/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

Paper ref

learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation

arXiv id

2602.12125

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

c8609e0b257b9acc0d5f76ea900b7f4fb6a42c05ec8553156320e01c5dc248f4

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/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation#webpage",
      "url": "https://sciencetostartup.com/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
      "name": "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation",
      "description": "Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation#scholarlyArticle",
      "headline": "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation",
      "description": "Develop a tool for enhanced on-policy distillation in reinforcement learning by leveraging reward extrapolation techniques for improved student performance.",
      "url": "https://sciencetostartup.com/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation",
      "sameAs": "https://arxiv.org/abs/2602.12125",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.12125"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-12T16:14:29.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "89e83ee3eb95843292b1f75f0e50b89e7667b828"
          },
          "url": "https://www.semanticscholar.org/paper/89e83ee3eb95843292b1f75f0e50b89e7667b828"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "370a293b5dcf9d456ba7f805b5b0a3d8e984ff6e"
          },
          "url": "https://www.semanticscholar.org/paper/370a293b5dcf9d456ba7f805b5b0a3d8e984ff6e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "06571d39f14fbd771423bf57c9a237faaf7994bf"
          },
          "url": "https://www.semanticscholar.org/paper/06571d39f14fbd771423bf57c9a237faaf7994bf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bda9e9b43c48b965024ff37de84f00edbbdf3f9c"
          },
          "url": "https://www.semanticscholar.org/paper/bda9e9b43c48b965024ff37de84f00edbbdf3f9c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "38bfb955426702f1bfc9888e52c9cd48b2f8757b"
          },
          "url": "https://www.semanticscholar.org/paper/38bfb955426702f1bfc9888e52c9cd48b2f8757b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c6d757cf650f7a7d87915b42a4e0023a00a85f54"
          },
          "url": "https://www.semanticscholar.org/paper/c6d757cf650f7a7d87915b42a4e0023a00a85f54"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b51114590dc5ef1f896204dcc5d9d61dec26946a"
          },
          "url": "https://www.semanticscholar.org/paper/b51114590dc5ef1f896204dcc5d9d61dec26946a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2e3d2cb75be2d8939387f9173b68cd81315ec694"
          },
          "url": "https://www.semanticscholar.org/paper/2e3d2cb75be2d8939387f9173b68cd81315ec694"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a29243393a7884afca18ae1854fd509859ae2697"
          },
          "url": "https://www.semanticscholar.org/paper/a29243393a7884afca18ae1854fd509859ae2697"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3f69fb7e93b20d04dfec182184b3c1d0a67d45ab"
          },
          "url": "https://www.semanticscholar.org/paper/3f69fb7e93b20d04dfec182184b3c1d0a67d45ab"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d5da014705059c44ed8c7b54a1660815a0eaee26"
          },
          "url": "https://www.semanticscholar.org/paper/d5da014705059c44ed8c7b54a1660815a0eaee26"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1839b34a1df105008fcdcda6502336fede9786da"
          },
          "url": "https://www.semanticscholar.org/paper/1839b34a1df105008fcdcda6502336fede9786da"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
          },
          "url": "https://www.semanticscholar.org/paper/d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b58ed3278832960ed88627dfa58799edb5ef3c88"
          },
          "url": "https://www.semanticscholar.org/paper/b58ed3278832960ed88627dfa58799edb5ef3c88"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "89713edb86935480d2223358de41104a72985ed4"
          },
          "url": "https://www.semanticscholar.org/paper/89713edb86935480d2223358de41104a72985ed4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d981ce332586e6a29f595cbdfa9347cf425e5cd0"
          },
          "url": "https://www.semanticscholar.org/paper/d981ce332586e6a29f595cbdfa9347cf425e5cd0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "73f60e2190180fbffd678b63993b56e95a2cf994"
          },
          "url": "https://www.semanticscholar.org/paper/73f60e2190180fbffd678b63993b56e95a2cf994"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b62d0605137463ea591a0619840305cb98f6958f"
          },
          "url": "https://www.semanticscholar.org/paper/b62d0605137463ea591a0619840305cb98f6958f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e23379a9752f57732d311f7a97af2c69af6fae7b"
          },
          "url": "https://www.semanticscholar.org/paper/e23379a9752f57732d311f7a97af2c69af6fae7b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9e576b3d5afd79791ead4d2a2a8bf5640b2de513"
          },
          "url": "https://www.semanticscholar.org/paper/9e576b3d5afd79791ead4d2a2a8bf5640b2de513"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Reinforcement Learning"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Reinforcement Learning",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Learning beyond Teacher: Generalized On-Policy Distillation ",
          "item": "https://sciencetostartup.com/paper/learning-beyond-teacher-generalized-on-policy-distillation-with-reward-extrapolation"
        }
      ]
    }
  ]
}

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(36)

Related Papers

Related Resources

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(36)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline