{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y62YRYAFU5UPKL3F35TPQBD4LB","short_pith_number":"pith:Y62YRYAF","canonical_record":{"source":{"id":"2406.08069","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T10:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50815554ad557243346ab18cdd1ae7af4336222d81b9ca918fb9ccc2d425a095","abstract_canon_sha256":"f6c1c0402126e764614b6a4a32a99e1ec288d16568ae4b3095438c0009c2fcfd"},"schema_version":"1.0"},"canonical_sha256":"c7b588e005a768f52f65df66f8047c5844f306e6e6a2974082e95d3919265523","source":{"kind":"arxiv","id":"2406.08069","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08069","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08069v3","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08069","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y62YRYAFU5UP","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y62YRYAFU5UPKL3F","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y62YRYAF","created_at":"2026-07-05T09:08:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y62YRYAFU5UPKL3F35TPQBD4LB","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08069","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T10:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50815554ad557243346ab18cdd1ae7af4336222d81b9ca918fb9ccc2d425a095","abstract_canon_sha256":"f6c1c0402126e764614b6a4a32a99e1ec288d16568ae4b3095438c0009c2fcfd"},"schema_version":"1.0"},"canonical_sha256":"c7b588e005a768f52f65df66f8047c5844f306e6e6a2974082e95d3919265523","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:26.472373Z","signature_b64":"iVPGgfcNhBX9VK4iCplzOWrWce2mXN8Wa7Yh0K+vK2F0ZReQ20crHEdDiAPuOKzdkGDMyEaNiaz1DPIotHoqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7b588e005a768f52f65df66f8047c5844f306e6e6a2974082e95d3919265523","last_reissued_at":"2026-07-05T09:08:26.471800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:26.471800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08069","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzgDLdfLxsolKO+CuxShGWdHkY+9yL0yp17/PdGk3e2+K/jiRqddnOfdgshdfQyTGjoTKYa/3OypnHnj8MksAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:39:55.199063Z"},"content_sha256":"86e44b6d9bbf2964c7109addadb71b616fd481c059e179f3ef50335258e07562","schema_version":"1.0","event_id":"sha256:86e44b6d9bbf2964c7109addadb71b616fd481c059e179f3ef50335258e07562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y62YRYAFU5UPKL3F35TPQBD4LB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Felix Kaubek, Matthijs T.J. Spaan, Max Weltevrede, Wendelin B\\\"ohmer","submitted_at":"2024-06-12T10:39:31Z","abstract_excerpt":"One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often framed in a multi-task setting where agents train on a fixed set of tasks and have to generalise to new tasks. Recent work has shown that in this setting increased exploration during training can be leveraged to increase the generalisation performance of the agent. This makes sense when the states encountered during testing can actually be explored during training. In this paper, we provide intuition why exploration ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08069","kind":"arxiv","version":3},"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/2406.08069/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":"2026-07-05T09:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6NVlrgts65qmNEqBN4WgXMPNO9JlNpBaE1785UCEiErO9uJhq0WDfa9A4USfqDX5jBT4jFq6pkLoML2QDN0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:39:55.199460Z"},"content_sha256":"9aa4ea9ed38c80c9673811327793f65b98d081571aeb0c4bcf55ddeb358df789","schema_version":"1.0","event_id":"sha256:9aa4ea9ed38c80c9673811327793f65b98d081571aeb0c4bcf55ddeb358df789"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/bundle.json","state_url":"https://pith.science/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/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":"2026-07-06T20:39:55Z","links":{"resolver":"https://pith.science/pith/Y62YRYAFU5UPKL3F35TPQBD4LB","bundle":"https://pith.science/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/bundle.json","state":"https://pith.science/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y62YRYAFU5UPKL3F35TPQBD4LB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y62YRYAFU5UPKL3F35TPQBD4LB","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":"f6c1c0402126e764614b6a4a32a99e1ec288d16568ae4b3095438c0009c2fcfd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T10:39:31Z","title_canon_sha256":"50815554ad557243346ab18cdd1ae7af4336222d81b9ca918fb9ccc2d425a095"},"schema_version":"1.0","source":{"id":"2406.08069","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08069","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08069v3","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08069","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y62YRYAFU5UP","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y62YRYAFU5UPKL3F","created_at":"2026-07-05T09:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y62YRYAF","created_at":"2026-07-05T09:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:9aa4ea9ed38c80c9673811327793f65b98d081571aeb0c4bcf55ddeb358df789","target":"graph","created_at":"2026-07-05T09:08:26Z","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/2406.08069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often framed in a multi-task setting where agents train on a fixed set of tasks and have to generalise to new tasks. Recent work has shown that in this setting increased exploration during training can be leveraged to increase the generalisation performance of the agent. This makes sense when the states encountered during testing can actually be explored during training. In this paper, we provide intuition why exploration ca","authors_text":"Felix Kaubek, Matthijs T.J. Spaan, Max Weltevrede, Wendelin B\\\"ohmer","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T10:39:31Z","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08069","kind":"arxiv","version":3},"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":"sha256:86e44b6d9bbf2964c7109addadb71b616fd481c059e179f3ef50335258e07562","target":"record","created_at":"2026-07-05T09:08:26Z","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":"f6c1c0402126e764614b6a4a32a99e1ec288d16568ae4b3095438c0009c2fcfd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T10:39:31Z","title_canon_sha256":"50815554ad557243346ab18cdd1ae7af4336222d81b9ca918fb9ccc2d425a095"},"schema_version":"1.0","source":{"id":"2406.08069","kind":"arxiv","version":3}},"canonical_sha256":"c7b588e005a768f52f65df66f8047c5844f306e6e6a2974082e95d3919265523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7b588e005a768f52f65df66f8047c5844f306e6e6a2974082e95d3919265523","first_computed_at":"2026-07-05T09:08:26.471800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:26.471800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iVPGgfcNhBX9VK4iCplzOWrWce2mXN8Wa7Yh0K+vK2F0ZReQ20crHEdDiAPuOKzdkGDMyEaNiaz1DPIotHoqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:26.472373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08069","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86e44b6d9bbf2964c7109addadb71b616fd481c059e179f3ef50335258e07562","sha256:9aa4ea9ed38c80c9673811327793f65b98d081571aeb0c4bcf55ddeb358df789"],"state_sha256":"74d2fb1eea54407c4e77fa408651644a65de59e9debc941552c2c4a5eab37f07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffC8XpNK/0/vn5Ta6d61Nmn0qqd/IhS31+9K5dVOzwdp9GyF8GZiYnKLvUe2CXBZmS/nLTRMn28zHUUv4UZDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:39:55.201549Z","bundle_sha256":"871809811e9982401cbeec8dede49f91987a6aa8c54cbae3e0d3afaa1b2674ff"}}