{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:433M6NYSDQL3CUBFTO5Y6UJ2HT","short_pith_number":"pith:433M6NYS","canonical_record":{"source":{"id":"2306.05727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:48:36Z","cross_cats_sorted":[],"title_canon_sha256":"1de43987b510ed05655e7766af53082831cbdc915baf4d3430a5edfa1f2a0a55","abstract_canon_sha256":"c28bb2d76ed9938593b3b89325166770fd0edc6946930f3cb9cc4b7c85ac401d"},"schema_version":"1.0"},"canonical_sha256":"e6f6cf37121c17b150259bbb8f513a3cc7f288bbc917db1c82751a141bc723d5","source":{"kind":"arxiv","id":"2306.05727","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05727","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05727v2","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05727","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"433M6NYSDQL3","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"433M6NYSDQL3CUBF","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"433M6NYS","created_at":"2026-07-05T06:46:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:433M6NYSDQL3CUBFTO5Y6UJ2HT","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:48:36Z","cross_cats_sorted":[],"title_canon_sha256":"1de43987b510ed05655e7766af53082831cbdc915baf4d3430a5edfa1f2a0a55","abstract_canon_sha256":"c28bb2d76ed9938593b3b89325166770fd0edc6946930f3cb9cc4b7c85ac401d"},"schema_version":"1.0"},"canonical_sha256":"e6f6cf37121c17b150259bbb8f513a3cc7f288bbc917db1c82751a141bc723d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:33.156585Z","signature_b64":"O9a1rBB6xp7amX/Xa51BUYLpvNyf0e2fyWHMYkDaQF551K4cnvQDzL8CIHmqKNmJe16GKgvNV71pBpdwigXTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6f6cf37121c17b150259bbb8f513a3cc7f288bbc917db1c82751a141bc723d5","last_reissued_at":"2026-07-05T06:46:33.156070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:33.156070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05727","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fU6mAMqFgvGFFgYay2m+X5rUdLV5I3W/m2pFJAAMKPk+n5mQkNiXyklHPRvAb11dAYPo/cvvnd4oLvZCteVeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:12:28.016253Z"},"content_sha256":"92a28f4a37cbfb71b5b9791237e24a6b3f3cfec2817b7216907ce9fc7af86c2a","schema_version":"1.0","event_id":"sha256:92a28f4a37cbfb71b5b9791237e24a6b3f3cfec2817b7216907ce9fc7af86c2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:433M6NYSDQL3CUBFTO5Y6UJ2HT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Role of Diverse Replay for Generalisation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthijs T.J. Spaan, Max Weltevrede, Wendelin B\\\"ohmer","submitted_at":"2023-06-09T07:48:36Z","abstract_excerpt":"In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL literature. In this paper, we investigate the impact of these components in the context of generalisation in multi-task RL. We investigate the hypothesis that collecting and training on more diverse data from the training environments will improve zero-shot generalisation to new tasks. We motivate mathematically and show empirically that generalisation to tasks th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05727","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/2306.05727/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":"2026-07-05T06:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQDOLWXMdfNAnmJJ5mj839ZGhLAsOjnzebrdvO3YRV2KvYax1QWq/gdx4Uq7MoabqRe6GPbmYkBREFZCB5GtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:12:28.016635Z"},"content_sha256":"599c3271512f906a7739dc729ef97e38657c9f90a79a40c6e59f337578cdaefa","schema_version":"1.0","event_id":"sha256:599c3271512f906a7739dc729ef97e38657c9f90a79a40c6e59f337578cdaefa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/bundle.json","state_url":"https://pith.science/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/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":"2026-07-07T14:12:28Z","links":{"resolver":"https://pith.science/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT","bundle":"https://pith.science/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/bundle.json","state":"https://pith.science/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/433M6NYSDQL3CUBFTO5Y6UJ2HT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:433M6NYSDQL3CUBFTO5Y6UJ2HT","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":"c28bb2d76ed9938593b3b89325166770fd0edc6946930f3cb9cc4b7c85ac401d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:48:36Z","title_canon_sha256":"1de43987b510ed05655e7766af53082831cbdc915baf4d3430a5edfa1f2a0a55"},"schema_version":"1.0","source":{"id":"2306.05727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05727","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05727v2","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05727","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"433M6NYSDQL3","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"433M6NYSDQL3CUBF","created_at":"2026-07-05T06:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"433M6NYS","created_at":"2026-07-05T06:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:599c3271512f906a7739dc729ef97e38657c9f90a79a40c6e59f337578cdaefa","target":"graph","created_at":"2026-07-05T06:46:33Z","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/2306.05727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL literature. In this paper, we investigate the impact of these components in the context of generalisation in multi-task RL. We investigate the hypothesis that collecting and training on more diverse data from the training environments will improve zero-shot generalisation to new tasks. We motivate mathematically and show empirically that generalisation to tasks th","authors_text":"Matthijs T.J. Spaan, Max Weltevrede, Wendelin B\\\"ohmer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:48:36Z","title":"The Role of Diverse Replay for Generalisation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05727","kind":"arxiv","version":2},"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":"sha256:92a28f4a37cbfb71b5b9791237e24a6b3f3cfec2817b7216907ce9fc7af86c2a","target":"record","created_at":"2026-07-05T06:46:33Z","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":"c28bb2d76ed9938593b3b89325166770fd0edc6946930f3cb9cc4b7c85ac401d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:48:36Z","title_canon_sha256":"1de43987b510ed05655e7766af53082831cbdc915baf4d3430a5edfa1f2a0a55"},"schema_version":"1.0","source":{"id":"2306.05727","kind":"arxiv","version":2}},"canonical_sha256":"e6f6cf37121c17b150259bbb8f513a3cc7f288bbc917db1c82751a141bc723d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6f6cf37121c17b150259bbb8f513a3cc7f288bbc917db1c82751a141bc723d5","first_computed_at":"2026-07-05T06:46:33.156070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:33.156070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O9a1rBB6xp7amX/Xa51BUYLpvNyf0e2fyWHMYkDaQF551K4cnvQDzL8CIHmqKNmJe16GKgvNV71pBpdwigXTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:33.156585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92a28f4a37cbfb71b5b9791237e24a6b3f3cfec2817b7216907ce9fc7af86c2a","sha256:599c3271512f906a7739dc729ef97e38657c9f90a79a40c6e59f337578cdaefa"],"state_sha256":"7ca6f6bd41bf288195abd9b862b3c745d536fd927bf317bc5107381561d90f86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FUrJivfuoHMAkd2E6k94nAQtjeALoZvR5B3uCPY6GhjfNUx38gsKfoA1l4VOSSkTsY1Yx39JDQ3floVvsYqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:12:28.018550Z","bundle_sha256":"c81a1c81f1e7062df05e27266e143135ff9681313ddecf96dd385054c3a993b5"}}