{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6HQOKBWRNYQ5FVLAWCUDTIWYN7","short_pith_number":"pith:6HQOKBWR","canonical_record":{"source":{"id":"1712.00378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T15:52:00Z","cross_cats_sorted":[],"title_canon_sha256":"71f0d83f6b6d223ac771c72702221d4ae758cebc14ca168c264ff568e99bf523","abstract_canon_sha256":"199b3be1fa244f447c23de9bbc59ce231030721f282dc86f15387e7f505a9a74"},"schema_version":"1.0"},"canonical_sha256":"f1e0e506d16e21d2d560b0a839a2d86fd70d996ad210278596ddec3b67f10582","source":{"kind":"arxiv","id":"1712.00378","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00378","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00378v4","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00378","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"6HQOKBWRNYQ5","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"6HQOKBWRNYQ5FVLA","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"6HQOKBWR","created_at":"2026-07-05T03:51:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6HQOKBWRNYQ5FVLAWCUDTIWYN7","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T15:52:00Z","cross_cats_sorted":[],"title_canon_sha256":"71f0d83f6b6d223ac771c72702221d4ae758cebc14ca168c264ff568e99bf523","abstract_canon_sha256":"199b3be1fa244f447c23de9bbc59ce231030721f282dc86f15387e7f505a9a74"},"schema_version":"1.0"},"canonical_sha256":"f1e0e506d16e21d2d560b0a839a2d86fd70d996ad210278596ddec3b67f10582","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:52.616200Z","signature_b64":"+NW2GzGrTYq0QuoGByZX2LoJJ5phv1IzFcqCU63Jywy1nTyZQnsSNY+10DFrbrqZ2lkBBaH+SApe6oQ2vBnDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1e0e506d16e21d2d560b0a839a2d86fd70d996ad210278596ddec3b67f10582","last_reissued_at":"2026-07-05T03:51:52.615748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:52.615748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00378","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"co9tuyPZdp7mwThEp2zDIq2ihdZa4+g6NviR3Gfi9rxyD3SjLQzkZ0EvO03vlf6ohWq76tD8z0frOw52RXjYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:29:52.690903Z"},"content_sha256":"1f793c7584766e31a83c13f870f68e7c82ec89e4a5b6ed64c8c8204b58172377","schema_version":"1.0","event_id":"sha256:1f793c7584766e31a83c13f870f68e7c82ec89e4a5b6ed64c8c8204b58172377"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6HQOKBWRNYQ5FVLAWCUDTIWYN7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Time Limits in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arash Tavakoli, Fabio Pardo, Petar Kormushev, Vitaly Levdik","submitted_at":"2017-12-01T15:52:00Z","abstract_excerpt":"In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state aliasing and invalidation of experience repla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00378","kind":"arxiv","version":4},"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/1712.00378/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":"2026-07-05T03:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHXHAF1cRhRbkgEYoZdjJ0uwT/zy97Hi6ARtiJU4NB/cW+KzAtOLpBs7alZVgg3zl8KvlbhFit3U3FXxFAR2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:29:52.691488Z"},"content_sha256":"d40a42467ab18ec05e76f986c2fb26a0a32227cb42eb19df8073ad6650eac2e4","schema_version":"1.0","event_id":"sha256:d40a42467ab18ec05e76f986c2fb26a0a32227cb42eb19df8073ad6650eac2e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/bundle.json","state_url":"https://pith.science/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/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":"2026-08-09T16:29:52Z","links":{"resolver":"https://pith.science/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7","bundle":"https://pith.science/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/bundle.json","state":"https://pith.science/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HQOKBWRNYQ5FVLAWCUDTIWYN7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6HQOKBWRNYQ5FVLAWCUDTIWYN7","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":"199b3be1fa244f447c23de9bbc59ce231030721f282dc86f15387e7f505a9a74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T15:52:00Z","title_canon_sha256":"71f0d83f6b6d223ac771c72702221d4ae758cebc14ca168c264ff568e99bf523"},"schema_version":"1.0","source":{"id":"1712.00378","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00378","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00378v4","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00378","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"6HQOKBWRNYQ5","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"6HQOKBWRNYQ5FVLA","created_at":"2026-07-05T03:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"6HQOKBWR","created_at":"2026-07-05T03:51:52Z"}],"graph_snapshots":[{"event_id":"sha256:d40a42467ab18ec05e76f986c2fb26a0a32227cb42eb19df8073ad6650eac2e4","target":"graph","created_at":"2026-07-05T03:51:52Z","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/1712.00378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state aliasing and invalidation of experience repla","authors_text":"Arash Tavakoli, Fabio Pardo, Petar Kormushev, Vitaly Levdik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T15:52:00Z","title":"Time Limits in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00378","kind":"arxiv","version":4},"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":"sha256:1f793c7584766e31a83c13f870f68e7c82ec89e4a5b6ed64c8c8204b58172377","target":"record","created_at":"2026-07-05T03:51:52Z","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":"199b3be1fa244f447c23de9bbc59ce231030721f282dc86f15387e7f505a9a74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T15:52:00Z","title_canon_sha256":"71f0d83f6b6d223ac771c72702221d4ae758cebc14ca168c264ff568e99bf523"},"schema_version":"1.0","source":{"id":"1712.00378","kind":"arxiv","version":4}},"canonical_sha256":"f1e0e506d16e21d2d560b0a839a2d86fd70d996ad210278596ddec3b67f10582","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1e0e506d16e21d2d560b0a839a2d86fd70d996ad210278596ddec3b67f10582","first_computed_at":"2026-07-05T03:51:52.615748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:52.615748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+NW2GzGrTYq0QuoGByZX2LoJJ5phv1IzFcqCU63Jywy1nTyZQnsSNY+10DFrbrqZ2lkBBaH+SApe6oQ2vBnDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:52.616200Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00378","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f793c7584766e31a83c13f870f68e7c82ec89e4a5b6ed64c8c8204b58172377","sha256:d40a42467ab18ec05e76f986c2fb26a0a32227cb42eb19df8073ad6650eac2e4"],"state_sha256":"d09f408d70a0375659ab0345bb1c853940a697de2bf22792ecaa512e42a1a528"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O8y6bH326EusgqfnH+kNlZ0I9qK8wfaXid1+tQK0GL6FSa4N/Tcko2eb+dbwXNws0wqK/FeGjRBMft5dHZXWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:29:52.696549Z","bundle_sha256":"05a4a7a4c073c78062b8c20173d65aa2c2df228cb1d7433fe1108afbd39017c9"}}