{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QFGKGRBZ4CXCN7HVKICB2JPMSK","short_pith_number":"pith:QFGKGRBZ","canonical_record":{"source":{"id":"2205.03353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-06T16:38:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"79f6f542c78b6f0553c554040f81bb34b03b4bda5f293919720917fbdc0609bb","abstract_canon_sha256":"a4b36e17b9a389a4392404fbc41d5b43ca68f92cd15033723401b5a798e66d56"},"schema_version":"1.0"},"canonical_sha256":"814ca34439e0ae26fcf552041d25ec929945743630f348dea0617fe88af5313c","source":{"kind":"arxiv","id":"2205.03353","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03353","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03353v1","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03353","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"QFGKGRBZ4CXC","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"QFGKGRBZ4CXCN7HV","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"QFGKGRBZ","created_at":"2026-07-05T04:20:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QFGKGRBZ4CXCN7HVKICB2JPMSK","target":"record","payload":{"canonical_record":{"source":{"id":"2205.03353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-06T16:38:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"79f6f542c78b6f0553c554040f81bb34b03b4bda5f293919720917fbdc0609bb","abstract_canon_sha256":"a4b36e17b9a389a4392404fbc41d5b43ca68f92cd15033723401b5a798e66d56"},"schema_version":"1.0"},"canonical_sha256":"814ca34439e0ae26fcf552041d25ec929945743630f348dea0617fe88af5313c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:58.979860Z","signature_b64":"hL0/AFoC5jxopUd0BsPSTxqd+9nT9mcsG0KKBzbyia+Na9GeMlYOTNGmtzYzd3oNxRHB0eYZGg+IWcB4m5pRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"814ca34439e0ae26fcf552041d25ec929945743630f348dea0617fe88af5313c","last_reissued_at":"2026-07-05T04:20:58.979379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:58.979379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.03353","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74om2/ExwmlLJbKhz+EhsCTp4oxgPKtO3zaU0YBhGbjHxFobbaSQ0Nq6jzhvVpGjoEO2+d9uyzgEcG84o4h0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:48:47.551471Z"},"content_sha256":"b1ea1960d024d51fe379a2102a585c6b6a6188f7493e0a2f8ecac0f36aa60967","schema_version":"1.0","event_id":"sha256:b1ea1960d024d51fe379a2102a585c6b6a6188f7493e0a2f8ecac0f36aa60967"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QFGKGRBZ4CXCN7HVKICB2JPMSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Abbas Abdolmaleki, Alex X. Lee, Coline Devin, Jost Tobias Springenberg, Konstantinos Bousmalis, Thomas Lampe, Yuxiang Zhou","submitted_at":"2022-05-06T16:38:59Z","abstract_excerpt":"Reinforcement learning (RL) has been shown to be effective at learning control from experience. However, RL typically requires a large amount of online interaction with the environment. This limits its applicability to real-world settings, such as in robotics, where such interaction is expensive. In this work we investigate ways to minimize online interactions in a target task, by reusing a suboptimal policy we might have access to, for example from training on related prior tasks, or in simulation. To this end, we develop two RL algorithms that can speed up training by using not only the acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03353","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/2205.03353/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZIDOeDpIZV0hU0Gdi3whyVCI9A0oVmnitbTX3nar+TweCEH/uFb+Y8z4ojnghUxLmHEcl2lnPQruQalvm1hCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:48:47.552043Z"},"content_sha256":"6e0de2ff8695b576abd6c13378c1af6e96024fa82d913dd21c77a37e386fb9bd","schema_version":"1.0","event_id":"sha256:6e0de2ff8695b576abd6c13378c1af6e96024fa82d913dd21c77a37e386fb9bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/bundle.json","state_url":"https://pith.science/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T20:48:47Z","links":{"resolver":"https://pith.science/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK","bundle":"https://pith.science/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/bundle.json","state":"https://pith.science/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFGKGRBZ4CXCN7HVKICB2JPMSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QFGKGRBZ4CXCN7HVKICB2JPMSK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a4b36e17b9a389a4392404fbc41d5b43ca68f92cd15033723401b5a798e66d56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-06T16:38:59Z","title_canon_sha256":"79f6f542c78b6f0553c554040f81bb34b03b4bda5f293919720917fbdc0609bb"},"schema_version":"1.0","source":{"id":"2205.03353","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03353","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03353v1","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03353","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"QFGKGRBZ4CXC","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"QFGKGRBZ4CXCN7HV","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"QFGKGRBZ","created_at":"2026-07-05T04:20:58Z"}],"graph_snapshots":[{"event_id":"sha256:6e0de2ff8695b576abd6c13378c1af6e96024fa82d913dd21c77a37e386fb9bd","target":"graph","created_at":"2026-07-05T04:20:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.03353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has been shown to be effective at learning control from experience. However, RL typically requires a large amount of online interaction with the environment. This limits its applicability to real-world settings, such as in robotics, where such interaction is expensive. In this work we investigate ways to minimize online interactions in a target task, by reusing a suboptimal policy we might have access to, for example from training on related prior tasks, or in simulation. To this end, we develop two RL algorithms that can speed up training by using not only the acti","authors_text":"Abbas Abdolmaleki, Alex X. Lee, Coline Devin, Jost Tobias Springenberg, Konstantinos Bousmalis, Thomas Lampe, Yuxiang Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-06T16:38:59Z","title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03353","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b1ea1960d024d51fe379a2102a585c6b6a6188f7493e0a2f8ecac0f36aa60967","target":"record","created_at":"2026-07-05T04:20:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a4b36e17b9a389a4392404fbc41d5b43ca68f92cd15033723401b5a798e66d56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-06T16:38:59Z","title_canon_sha256":"79f6f542c78b6f0553c554040f81bb34b03b4bda5f293919720917fbdc0609bb"},"schema_version":"1.0","source":{"id":"2205.03353","kind":"arxiv","version":1}},"canonical_sha256":"814ca34439e0ae26fcf552041d25ec929945743630f348dea0617fe88af5313c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814ca34439e0ae26fcf552041d25ec929945743630f348dea0617fe88af5313c","first_computed_at":"2026-07-05T04:20:58.979379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:58.979379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hL0/AFoC5jxopUd0BsPSTxqd+9nT9mcsG0KKBzbyia+Na9GeMlYOTNGmtzYzd3oNxRHB0eYZGg+IWcB4m5pRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:58.979860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03353","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ea1960d024d51fe379a2102a585c6b6a6188f7493e0a2f8ecac0f36aa60967","sha256:6e0de2ff8695b576abd6c13378c1af6e96024fa82d913dd21c77a37e386fb9bd"],"state_sha256":"ec39b264e8d895ef2ed69ad5777dc54470c5ac7822b5e643e53a73216980996e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+M5mrPX9k7y/sjCCvPHUa2AqMeEOQ+l1cSL8/kksPBOZNT9GyQrOOcIGQ1VtmqOulgBJhKDOUj8W6gazsJOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:48:47.556699Z","bundle_sha256":"89c18fba97ae0cf3bacebdd120b79e4842f5b4025aab423aadd19a85f2879c7c"}}