{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PKLDT46YMKUOKYTYVRGKKMVIC4","short_pith_number":"pith:PKLDT46Y","schema_version":"1.0","canonical_sha256":"7a9639f3d862a8e56278ac4ca532a8173c7d0df0320a2c1f82ffb6d8d23080d8","source":{"kind":"arxiv","id":"1911.00357","version":2},"attestation_state":"computed","paper":{"title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Kadian, Ari Morcos, Devi Parikh, Dhruv Batra, Erik Wijmans, Irfan Essa, Manolis Savva, Stefan Lee","submitted_at":"2019-11-01T13:07:37Z","abstract_excerpt":"We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever stale), making it conceptually simple and easy to implement. In our experiments on training virtual robots to navigate in Habitat-Sim, DD-PPO exhibits near-linear scaling -- achieving a speedup of 107x on 128 GPUs over a serial implementation. We leverage this scaling to train an agent for 2.5 Bil"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.00357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-01T13:07:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28844b1bdb4aadd0aa53c0593a2c0f954150fa81db6bb0afa98ba99f4336a3a8","abstract_canon_sha256":"9bc8dbea0153d0705d8b228ab2c4a0a7b4eecd628a74de5c621d5d502304de76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:34:19.057135Z","signature_b64":"BwNL2RUP4DphmAUUmqCl1wMVOm4nZ9+uAM6BURMnfMRF/mEURNc3Oq2VykVEXtCMTYVBdWYJG4if3Bq1wq0WAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a9639f3d862a8e56278ac4ca532a8173c7d0df0320a2c1f82ffb6d8d23080d8","last_reissued_at":"2026-07-05T00:34:19.056642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:34:19.056642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Kadian, Ari Morcos, Devi Parikh, Dhruv Batra, Erik Wijmans, Irfan Essa, Manolis Savva, Stefan Lee","submitted_at":"2019-11-01T13:07:37Z","abstract_excerpt":"We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever stale), making it conceptually simple and easy to implement. In our experiments on training virtual robots to navigate in Habitat-Sim, DD-PPO exhibits near-linear scaling -- achieving a speedup of 107x on 128 GPUs over a serial implementation. We leverage this scaling to train an agent for 2.5 Bil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00357","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.00357/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.00357","created_at":"2026-07-05T00:34:19.056702+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00357v2","created_at":"2026-07-05T00:34:19.056702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00357","created_at":"2026-07-05T00:34:19.056702+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKLDT46YMKUO","created_at":"2026-07-05T00:34:19.056702+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKLDT46YMKUOKYTY","created_at":"2026-07-05T00:34:19.056702+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKLDT46Y","created_at":"2026-07-05T00:34:19.056702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25119","citing_title":"SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21587","citing_title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18888","citing_title":"Generative-Model Predictive Planning for Navigation in Partially Observable Environments","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18235","citing_title":"EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08029","citing_title":"IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26239","citing_title":"Sentinel: Embodied Cooperative Spatial Reasoning and Planning","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27871","citing_title":"LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28237","citing_title":"POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01313","citing_title":"PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00338","citing_title":"Scalable Option Learning in High-Throughput Environments","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16445","citing_title":"FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20685","citing_title":"C-NAV: Towards Self-Evolving Continual Object Navigation in Open World","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04320","citing_title":"MacroNav: Multi-Task Context Representation Learning Enables Efficient Navigation in Unknown Environments","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16806","citing_title":"Insect-inspired Visual Point-goal Navigation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20530","citing_title":"Memory Over Maps: 3D Object Localization Without Reconstruction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26788","citing_title":"ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11762","citing_title":"NavOL: Navigation Policy with Online Imitation Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05960","citing_title":"Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12626","citing_title":"Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17407","citing_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4","json":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4.json","graph_json":"https://pith.science/api/pith-number/PKLDT46YMKUOKYTYVRGKKMVIC4/graph.json","events_json":"https://pith.science/api/pith-number/PKLDT46YMKUOKYTYVRGKKMVIC4/events.json","paper":"https://pith.science/paper/PKLDT46Y"},"agent_actions":{"view_html":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4","download_json":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4.json","view_paper":"https://pith.science/paper/PKLDT46Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00357&json=true","fetch_graph":"https://pith.science/api/pith-number/PKLDT46YMKUOKYTYVRGKKMVIC4/graph.json","fetch_events":"https://pith.science/api/pith-number/PKLDT46YMKUOKYTYVRGKKMVIC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4/action/storage_attestation","attest_author":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4/action/author_attestation","sign_citation":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4/action/citation_signature","submit_replication":"https://pith.science/pith/PKLDT46YMKUOKYTYVRGKKMVIC4/action/replication_record"}},"created_at":"2026-07-05T00:34:19.056702+00:00","updated_at":"2026-07-05T00:34:19.056702+00:00"}