{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2RI7TRMOVPH6O74WBQ6F74T3AR","short_pith_number":"pith:2RI7TRMO","schema_version":"1.0","canonical_sha256":"d451f9c58eabcfe77f960c3c5ff27b04750c8418cfc0bc7ec10fdee1c7229050","source":{"kind":"arxiv","id":"2202.13657","version":2},"attestation_state":"computed","paper":{"title":"Avalanche RL: a Continual Reinforcement Learning Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Antonio Carta, Davide Bacciu, Nicol\\`o Lucchesi, Vincenzo Lomonaco","submitted_at":"2022-02-28T10:01:22Z","abstract_excerpt":"Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanche RL, a library for Continual Reinforcement Learning which allows to easily train agents on a continuous stream of tasks. Avalanche RL is based on PyTorch and supports any OpenAI Gym environment. Its design is based on Avalanche, one of the more popular continual learning libraries, which allow us to reuse a large number of continual learning strategies and improve the interact"},"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":"2202.13657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T10:01:22Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"aab7e7bf9d22a024c18c7e25b69f56b7df8bda7d84e2567927c248bcc955b092","abstract_canon_sha256":"f879fb9561f0931861be8cc86c0532b746184bae0cfef141f129ce61a90f96a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:17.993668Z","signature_b64":"VSdqu+7vhqP8rxv/g7HqsljU6cNi3u1OPTv2g4tyKvtnDhXlSdoiWVXhIy/kNlzuXkP7nHA/2bgjSNZ2p16qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d451f9c58eabcfe77f960c3c5ff27b04750c8418cfc0bc7ec10fdee1c7229050","last_reissued_at":"2026-07-05T04:08:17.993231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:17.993231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Avalanche RL: a Continual Reinforcement Learning Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Antonio Carta, Davide Bacciu, Nicol\\`o Lucchesi, Vincenzo Lomonaco","submitted_at":"2022-02-28T10:01:22Z","abstract_excerpt":"Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanche RL, a library for Continual Reinforcement Learning which allows to easily train agents on a continuous stream of tasks. Avalanche RL is based on PyTorch and supports any OpenAI Gym environment. Its design is based on Avalanche, one of the more popular continual learning libraries, which allow us to reuse a large number of continual learning strategies and improve the interact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13657","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/2202.13657/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":"2202.13657","created_at":"2026-07-05T04:08:17.993284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13657v2","created_at":"2026-07-05T04:08:17.993284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13657","created_at":"2026-07-05T04:08:17.993284+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RI7TRMOVPH6","created_at":"2026-07-05T04:08:17.993284+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RI7TRMOVPH6O74W","created_at":"2026-07-05T04:08:17.993284+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RI7TRMO","created_at":"2026-07-05T04:08:17.993284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16532","citing_title":"Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR","json":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR.json","graph_json":"https://pith.science/api/pith-number/2RI7TRMOVPH6O74WBQ6F74T3AR/graph.json","events_json":"https://pith.science/api/pith-number/2RI7TRMOVPH6O74WBQ6F74T3AR/events.json","paper":"https://pith.science/paper/2RI7TRMO"},"agent_actions":{"view_html":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR","download_json":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR.json","view_paper":"https://pith.science/paper/2RI7TRMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13657&json=true","fetch_graph":"https://pith.science/api/pith-number/2RI7TRMOVPH6O74WBQ6F74T3AR/graph.json","fetch_events":"https://pith.science/api/pith-number/2RI7TRMOVPH6O74WBQ6F74T3AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR/action/storage_attestation","attest_author":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR/action/author_attestation","sign_citation":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR/action/citation_signature","submit_replication":"https://pith.science/pith/2RI7TRMOVPH6O74WBQ6F74T3AR/action/replication_record"}},"created_at":"2026-07-05T04:08:17.993284+00:00","updated_at":"2026-07-05T04:08:17.993284+00:00"}