{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "jumanji-scalable-environments-2023", "title": "Jumanji scalable compositional JAX environments", "summary": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments.", "boundary": "Original v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.", "area": "Reinforcement learning simulation infrastructure", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "BENCHMARK", "contribution_kind": "EVALUATION_RESOURCE_DESIGN", "package_id": "jumanji-scalable-environments-2023", "target": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "humans": [ "Clément Bonnet", "Daniel Luo", "Donal Byrne", "Shikha Surana", "Vincent Coyette", "Paul Duckworth", "Laurence I. Midgley", "Tristan Kalloniatis", "Sasha Abramowitz", "Cemlyn N. Waters", "Andries P. Smit", "Nathan Grinsztajn", "Ulrich A. Mbou Sob", "Omayma Mahjoub", "Elshadai Tegegn", "Mohamed A. Mimouni", "Raphael Boige", "Ruan de Kock", "Daniel Furelos-Blanco", "Victor Le", "Arnu Pretorius", "Alexandre Laterre" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "ai-oct15-arxiv-2306-09884v1", "title": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } ], "points": "65000", "published_grade": { "id": "jumanji-scalable-environments-2023", "entry_id": "jumanji-scalable-environments-2023", "band": "B", "modifier": "+", "target": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "what_changed": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments.", "scope": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments. Original v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Clément Bonnet", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Daniel Luo", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Donal Byrne", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shikha Surana", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Vincent Coyette", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Paul Duckworth", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Laurence I. Midgley", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tristan Kalloniatis", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sasha Abramowitz", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Cemlyn N. Waters", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andries P. Smit", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nathan Grinsztajn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ulrich A. Mbou Sob", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Omayma Mahjoub", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Elshadai Tegegn", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mohamed A. Mimouni", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Raphael Boige", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ruan de Kock", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Daniel Furelos-Blanco", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Victor Le", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Arnu Pretorius", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alexandre Laterre", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Original v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.", "domain": "Reinforcement learning simulation infrastructure" }, "sources": [ { "citation": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1" } ], "statement": "# Jumanji scalable compositional JAX environments\n\nProvides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments.\n\n## Scientific scope\n\nOriginal v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nClément Bonnet; Daniel Luo; Donal Byrne; Shikha Surana; Vincent Coyette; Paul Duckworth; Laurence I. Midgley; Tristan Kalloniatis; Sasha Abramowitz; Cemlyn N. Waters; Andries P. Smit; Nathan Grinsztajn; Ulrich A. Mbou Sob; Omayma Mahjoub; Elshadai Tegegn; Mohamed A. Mimouni; Raphael Boige; Ruan de Kock; Daniel Furelos-Blanco; Victor Le; Arnu Pretorius; Alexandre Laterre\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX](https://arxiv.org/pdf/2306.09884v1)\n", "summary": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments.", "title": "Jumanji scalable compositional JAX environments" }, "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "source_ref": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:dd83576d9472f5056421e099a0da6102aed378f7b93dfb51fa45926ff0129254" }, "target": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "jumanji-scalable-environments-2023", "entry_id": "jumanji-scalable-environments-2023", "revision": 1, "title": "Jumanji scalable compositional JAX environments", "context": "Reinforcement learning simulation infrastructure", "track": "Evaluation resource design", "band": "B", "modifier": "+", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments.", "scope": "Provides accelerator-native routing/packing/logic environments with customizable initial-state generators, reset/reward/viewer components and actor-critic baselines for scalable experiments. Original v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original v1 has22authors and18environments, not the later official site's24authors/22environments. NP-hard problem environments do not imply polynomial-time exact solvers. Hardware acceleration and selected generalization experiments do not establish arbitrary real-world transfer. First-author star is correspondence.", "references": [ { "title": "Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX", "url": "https://arxiv.org/pdf/2306.09884v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:db7c55e0-9adf-4d65-a3d3-87b306ddd747", "version": 1, "content_hash": "sha256:99a225fd2669df0ad8e3725613bd50444278369eb02864bbd41b91a9fab9debc" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "65000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }