ARXIV:2602.22786 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

arXiv

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning. However, their reliance on the max operator for temporal-difference (TD) target calculation leads to…

METHOD

Full abstract

Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies. To address this problem, we propose QSIM, a similarity weighted Q-learning framework that reconstructs the TD target using action similarity. Instead of using the greedy joint action directly, QSIM forms a similarity weighted expectation over a structured near-greedy joint action space. This formulation allows the target to integrate Q-values from diverse yet behaviorally related actions while assigning greater influence to those that are more similar to the greedy choice. By smoothing the target with structurally relevant alternatives, QSIM effectively mitigates overestimation and improves learning stability. Extensive experiments demonstrate that QSIM can be seamlessly integrated with various VD methods, consistently yielding superior performance and stability compared to the original algorithms. Furthermore, empirical analysis confirms that QSIM significantly mitigates the systematic value overestimation in MARL. Code is available at https://github.com/MaoMaoLYJ/pymarl-qsim.

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and…

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 6.0/10.

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

Opportunity summary

Score6.0

PainDevelop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

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

ARXIV:2602.22786 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

arXiv

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

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 6.0/10.

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

Opportunity summary

Score6.0

PainDevelop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

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

Paper Pack

10.48550/arXiv.2602.22786

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

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 fallback25 indexednot indexed

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

Viability

6.0

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 6.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning. However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 6.0/10 on the public viability pass. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies.
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 6.0/10.
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 QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.

Segment

Reinforcement Learning

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.22786 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(25)

Symmetry-Informed MARL: A Decentralized and Cooperative UAV Swarm Control Approach for Communication Coverage

2025Rongye Shi, Xin Yu et al.

Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation

2025Dapeng Li, Na Lou et al.

Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey

2024Ruiqi Zhang, Jing Hou et al.

On fair traffic allocation and efficient utilization of network resources based on MARL

2024E. P. Stepanov, R. Smelyanskiy et al.

Safe Multiagent Reinforcement Learning With Bilevel Optimization in Autonomous Driving

2024Zhi Zheng, Shangding Gu

Regularized Softmax Deep Multi-Agent Q-Learning

2021L. Pan, Tabish Rashid et al.

Learning to Represent Action Values as a Hypergraph on the Action Vertices

2020Arash Tavakoli, Mehdi Fatemi et al.

RODE: Learning Roles to Decompose Multi-Agent Tasks

2020Tonghan Wang, Tarun Gupta et al.

QPLEX: Duplex Dueling Multi-Agent Q-Learning

2020Jianhao Wang, Zhizhou Ren et al.

Weighted QMIX: Expanding Monotonic Value Function Factorisation

2020Tabish Rashid, Gregory Farquhar et al.

Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks

2020Georgios Papoudakis, Filippos Christianos et al.

Reinforcement learning

2020F. Wörgötter, B. Porr

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

2020Tabish Rashid, Mikayel Samvelyan et al.

ROMA: Multi-Agent Reinforcement Learning with Emergent Roles

2020Tonghan Wang, Heng Dong et al.

MAVEN: Multi-Agent Variational Exploration

2019Anuj Mahajan, Tabish Rashid et al.

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

2019Kyunghwan Son, Daewoo Kim et al.

The StarCraft Multi-Agent Challenge

2019Mikayel Samvelyan, Tabish Rashid et al.

Learning Action Representations for Reinforcement Learning

2019Yash Chandak, Georgios Theocharous et al.

Value-Decomposition Networks For Cooperative Multi-Agent Learning

2017P. Sunehag, Guy Lever et al.

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

2017Ryan Lowe, Yi Wu et al.

Showing 20 of 25 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 WorkDistributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization

6.0

Extension

Builds On ThisMA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings

3.0

Builds On ThisStrategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation

4.0

Commercially relevant

Higher ViabilityBreakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning

7.0

Higher ViabilityBest-of-Q: Improving VLM agents with Q-function Action Ranking at Inference

7.0

Higher ViabilityLearning Partial Action Replacement in Offline MARL

7.0

Higher ViabilityBeyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks

7.0

Higher ViabilityAgent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

7.0

Higher ViabilitySimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning

8.0

Conflicting

Competing ApproachRetaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning

6.0

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: 2602.22786
Route: /paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning
Active tab: read
Artifact: qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning/paper-pack
REST build passport API/api/v1/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning/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": "f3141528-cae5-4d36-8768-14e1fb3c63d4",
  "arxiv_id": "2602.22786",
  "canonical_route": "/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
  "endpoints": {
    "paper_pack": "/api/v1/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning/paper-pack",
    "build_passport": "/api/v1/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning/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/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

stale

Proof freshness: stale
Proof status: unverified
Display score: 6/10
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

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Canonical ID qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning | Route /paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.22786"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning",
  "normalized_query": "2602.22786",
  "route": "/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
  "paper_ref": "qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
  "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: QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

/buildability/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

Watchwatch

Subject: QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

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/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

Paper ref

qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning

arXiv id

2602.22786

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

404ca54c7fb31b40c764650e069931afb0b2a1671acbfb2c09bbad8f2044ec9e

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/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning#webpage",
      "url": "https://sciencetostartup.com/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
      "name": "QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning",
      "description": "Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning#scholarlyArticle",
      "headline": "QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning",
      "description": "Develop QSIM to enhance stability and performance in multi-agent reinforcement learning by mitigating Q-value overestimation using action similarity weighted Q-learning.",
      "url": "https://sciencetostartup.com/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning",
      "sameAs": "https://arxiv.org/abs/2602.22786",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.22786"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-26T09:20:46.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c68ef987429f50c986b44c0744b2c2ea3f7a8a05"
          },
          "url": "https://www.semanticscholar.org/paper/c68ef987429f50c986b44c0744b2c2ea3f7a8a05"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3a5591e7730d8bb9212bbb749bdd5364d5188e04"
          },
          "url": "https://www.semanticscholar.org/paper/3a5591e7730d8bb9212bbb749bdd5364d5188e04"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e207c5dd3af449ecc0f43c76e968d3955ed3c497"
          },
          "url": "https://www.semanticscholar.org/paper/e207c5dd3af449ecc0f43c76e968d3955ed3c497"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1fba32334ebface5029ae15964bfd61104a32b65"
          },
          "url": "https://www.semanticscholar.org/paper/1fba32334ebface5029ae15964bfd61104a32b65"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "dc89f9dc1c94a782163f8757dc6f71ecfcfc9669"
          },
          "url": "https://www.semanticscholar.org/paper/dc89f9dc1c94a782163f8757dc6f71ecfcfc9669"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5b2e36e7991dcf1b0b10dddf6a0e69b7641f1ed7"
          },
          "url": "https://www.semanticscholar.org/paper/5b2e36e7991dcf1b0b10dddf6a0e69b7641f1ed7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "467658037d60be494126f8c00974fb30593403f1"
          },
          "url": "https://www.semanticscholar.org/paper/467658037d60be494126f8c00974fb30593403f1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5764095b0186a3fc3832c1052aa14996a5927edc"
          },
          "url": "https://www.semanticscholar.org/paper/5764095b0186a3fc3832c1052aa14996a5927edc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "052c100d45f949c06e8419b504e319b442cb3f0a"
          },
          "url": "https://www.semanticscholar.org/paper/052c100d45f949c06e8419b504e319b442cb3f0a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1c4809748affb4d4f24d013ab4cd1b58ce4bd1f1"
          },
          "url": "https://www.semanticscholar.org/paper/1c4809748affb4d4f24d013ab4cd1b58ce4bd1f1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4ec9c22bb689dd136726cfe4159344066f681cfb"
          },
          "url": "https://www.semanticscholar.org/paper/4ec9c22bb689dd136726cfe4159344066f681cfb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8c11f3676c33eaf9bfc2801b93d531cf6cbcaa28"
          },
          "url": "https://www.semanticscholar.org/paper/8c11f3676c33eaf9bfc2801b93d531cf6cbcaa28"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3f5f13c6f5c659754086a7faa51d6bc60f577cd1"
          },
          "url": "https://www.semanticscholar.org/paper/3f5f13c6f5c659754086a7faa51d6bc60f577cd1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5e8350467d7d19e1d5f991be23f7b4826a9303a8"
          },
          "url": "https://www.semanticscholar.org/paper/5e8350467d7d19e1d5f991be23f7b4826a9303a8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c38e624c8d176153a23ada19978f334c9ec94bae"
          },
          "url": "https://www.semanticscholar.org/paper/c38e624c8d176153a23ada19978f334c9ec94bae"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "56ca9b304e0476feaa6dd4fd1cccc8c0a1a9d8eb"
          },
          "url": "https://www.semanticscholar.org/paper/56ca9b304e0476feaa6dd4fd1cccc8c0a1a9d8eb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "82055eed2ba0d7156a54c586249742c848e5d565"
          },
          "url": "https://www.semanticscholar.org/paper/82055eed2ba0d7156a54c586249742c848e5d565"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4c54efd3b9ce84f4268b165f5896c0692a50bcd1"
          },
          "url": "https://www.semanticscholar.org/paper/4c54efd3b9ce84f4268b165f5896c0692a50bcd1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "250bf5e1d40a619080dec553914c2905db6008c7"
          },
          "url": "https://www.semanticscholar.org/paper/250bf5e1d40a619080dec553914c2905db6008c7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7c3ece1ba41c415d7e81cfa5ca33a8de66efd434"
          },
          "url": "https://www.semanticscholar.org/paper/7c3ece1ba41c415d7e81cfa5ca33a8de66efd434"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 6
        },
        {
          "@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": "QSIM: Mitigating Overestimation in Multi-Agent Reinforcement",
          "item": "https://sciencetostartup.com/paper/qsim-mitigating-overestimation-in-multi-agent-reinforcement-learning-via-action-similarity-weighted-q-learning"
        }
      ]
    }
  ]
}

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(25)

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(25)

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