{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B3EASGN6EVLWLMGNF7ZV5VT5WX","short_pith_number":"pith:B3EASGN6","schema_version":"1.0","canonical_sha256":"0ec80919be255765b0cd2ff35ed67db5d6cbd35f093de686acf13b2c2c6cc43d","source":{"kind":"arxiv","id":"2006.12478","version":1},"attestation_state":"computed","paper":{"title":"Ecological Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Glen Berseth, John D. Co-Reyes, Sergey Levine, Suvansh Sanjeev","submitted_at":"2020-06-22T17:55:03Z","abstract_excerpt":"Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must learn through continuous interaction with the world without resets, and where the agent receives only delayed and sparse reward signals, is substantially more difficult, but arguably more realistic considering real-world environments do not present the learner with a convenient \"reset mechanism\" and easy reward shaping. In this paper, instead of studying algori"},"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":"2006.12478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T17:55:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5d49ffae8202e81a13b68b303edf457ee7e9c773aa0e2f4c3db38b24a79958eb","abstract_canon_sha256":"04e3cd964e6ff2cf673036c86698b65bcc8dc1095f7dfb75843b674551939eeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:00.908343Z","signature_b64":"q2kYZHnvN1TBKBVbw69EzzNb9OzZJ/smkWfAETMpBA4Eyt6APcI7FaM4V8R2j9cQCE+D8ii/54rlHYYnmR9ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec80919be255765b0cd2ff35ed67db5d6cbd35f093de686acf13b2c2c6cc43d","last_reissued_at":"2026-07-05T01:12:00.907837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:00.907837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ecological Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Glen Berseth, John D. Co-Reyes, Sergey Levine, Suvansh Sanjeev","submitted_at":"2020-06-22T17:55:03Z","abstract_excerpt":"Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must learn through continuous interaction with the world without resets, and where the agent receives only delayed and sparse reward signals, is substantially more difficult, but arguably more realistic considering real-world environments do not present the learner with a convenient \"reset mechanism\" and easy reward shaping. In this paper, instead of studying algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12478","kind":"arxiv","version":1},"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/2006.12478/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":"2006.12478","created_at":"2026-07-05T01:12:00.907885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12478v1","created_at":"2026-07-05T01:12:00.907885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12478","created_at":"2026-07-05T01:12:00.907885+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3EASGN6EVLW","created_at":"2026-07-05T01:12:00.907885+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3EASGN6EVLWLMGN","created_at":"2026-07-05T01:12:00.907885+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3EASGN6","created_at":"2026-07-05T01:12:00.907885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07460","citing_title":"Social-spatial dependencies for learning visual navigation","ref_index":208,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX","json":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX.json","graph_json":"https://pith.science/api/pith-number/B3EASGN6EVLWLMGNF7ZV5VT5WX/graph.json","events_json":"https://pith.science/api/pith-number/B3EASGN6EVLWLMGNF7ZV5VT5WX/events.json","paper":"https://pith.science/paper/B3EASGN6"},"agent_actions":{"view_html":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX","download_json":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX.json","view_paper":"https://pith.science/paper/B3EASGN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12478&json=true","fetch_graph":"https://pith.science/api/pith-number/B3EASGN6EVLWLMGNF7ZV5VT5WX/graph.json","fetch_events":"https://pith.science/api/pith-number/B3EASGN6EVLWLMGNF7ZV5VT5WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX/action/storage_attestation","attest_author":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX/action/author_attestation","sign_citation":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX/action/citation_signature","submit_replication":"https://pith.science/pith/B3EASGN6EVLWLMGNF7ZV5VT5WX/action/replication_record"}},"created_at":"2026-07-05T01:12:00.907885+00:00","updated_at":"2026-07-05T01:12:00.907885+00:00"}