{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5AGUSWYXKQGBHCJATHVFEAHVF6","short_pith_number":"pith:5AGUSWYX","canonical_record":{"source":{"id":"2002.06038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T13:57:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0570fb2bf01b3e335135e8f38954a4c32790e8960468ae9e62e64b26f472ba8b","abstract_canon_sha256":"f9f9149bc531f52db291940894e90538d466df0e15a95ec3b0ef86eeb3e65064"},"schema_version":"1.0"},"canonical_sha256":"e80d495b17540c13892099ea5200f52fae842bda6462992b7a64822776cf301b","source":{"kind":"arxiv","id":"2002.06038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06038","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06038v1","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06038","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"5AGUSWYXKQGB","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_16","alias_value":"5AGUSWYXKQGBHCJA","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_8","alias_value":"5AGUSWYX","created_at":"2026-07-05T00:40:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5AGUSWYXKQGBHCJATHVFEAHVF6","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T13:57:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0570fb2bf01b3e335135e8f38954a4c32790e8960468ae9e62e64b26f472ba8b","abstract_canon_sha256":"f9f9149bc531f52db291940894e90538d466df0e15a95ec3b0ef86eeb3e65064"},"schema_version":"1.0"},"canonical_sha256":"e80d495b17540c13892099ea5200f52fae842bda6462992b7a64822776cf301b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:49.417883Z","signature_b64":"Uc/0D5Kze4B4nlyW8IQAKR73Zc73+JUHXddmEgwzDRUExCJ1kIIg9R7FklaZRkI0B4f3qNtV5uvwbC2CiR71Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e80d495b17540c13892099ea5200f52fae842bda6462992b7a64822776cf301b","last_reissued_at":"2026-07-05T00:40:49.417502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:49.417502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06038","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":"2026-07-05T00:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQW3yKsoTK07udhFZhfIa1AeLoNR4202Jx8nEJPRlBn+nSM4NhRol40MvHTXC9h0Kkk9R9TMX+7XR3OjA+GHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:18:04.949900Z"},"content_sha256":"081f695a8a06d423903248727a7cc4a1272a36174002289fafcf5933c99d665f","schema_version":"1.0","event_id":"sha256:081f695a8a06d423903248727a7cc4a1272a36174002289fafcf5933c99d665f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5AGUSWYXKQGBHCJATHVFEAHVF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Never Give Up: Learning Directed Exploration Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alexander Pritzel, Alex Vitvitskyi, Andew Bolt, Bilal Piot, Charles Blundell, Daniel Guo, Mart\\'in Arjovsky, Olivier Tieleman, Pablo Sprechmann, Steven Kapturowski","submitted_at":"2020-02-14T13:57:22Z","abstract_excerpt":"We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment. A self-supervised inverse dynamics model is used to train the embeddings of the nearest neighbour lookup, biasing the novelty signal towards what the agent can control. We employ the framework of Universal Value Function Approxim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06038","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/2002.06038/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":"2026-07-05T00:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8wfNars9r05s3rxVHyU1YGEfKHfpu74gICSpE5750+F2DIxhOsfsDyDYOZV1w43TvJC0lIex6+5BH4U1lmHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:18:04.950405Z"},"content_sha256":"b275acc9af0c3fc86104d9c932765efc9c79b260b3b5be3a4929ffb3df4a39b4","schema_version":"1.0","event_id":"sha256:b275acc9af0c3fc86104d9c932765efc9c79b260b3b5be3a4929ffb3df4a39b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/bundle.json","state_url":"https://pith.science/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/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":"2026-08-10T18:18:04Z","links":{"resolver":"https://pith.science/pith/5AGUSWYXKQGBHCJATHVFEAHVF6","bundle":"https://pith.science/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/bundle.json","state":"https://pith.science/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AGUSWYXKQGBHCJATHVFEAHVF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5AGUSWYXKQGBHCJATHVFEAHVF6","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":"f9f9149bc531f52db291940894e90538d466df0e15a95ec3b0ef86eeb3e65064","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T13:57:22Z","title_canon_sha256":"0570fb2bf01b3e335135e8f38954a4c32790e8960468ae9e62e64b26f472ba8b"},"schema_version":"1.0","source":{"id":"2002.06038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06038","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06038v1","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06038","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"5AGUSWYXKQGB","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_16","alias_value":"5AGUSWYXKQGBHCJA","created_at":"2026-07-05T00:40:49Z"},{"alias_kind":"pith_short_8","alias_value":"5AGUSWYX","created_at":"2026-07-05T00:40:49Z"}],"graph_snapshots":[{"event_id":"sha256:b275acc9af0c3fc86104d9c932765efc9c79b260b3b5be3a4929ffb3df4a39b4","target":"graph","created_at":"2026-07-05T00:40:49Z","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/2002.06038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment. A self-supervised inverse dynamics model is used to train the embeddings of the nearest neighbour lookup, biasing the novelty signal towards what the agent can control. We employ the framework of Universal Value Function Approxim","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alexander Pritzel, Alex Vitvitskyi, Andew Bolt, Bilal Piot, Charles Blundell, Daniel Guo, Mart\\'in Arjovsky, Olivier Tieleman, Pablo Sprechmann, Steven Kapturowski","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T13:57:22Z","title":"Never Give Up: Learning Directed Exploration Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06038","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":"sha256:081f695a8a06d423903248727a7cc4a1272a36174002289fafcf5933c99d665f","target":"record","created_at":"2026-07-05T00:40:49Z","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":"f9f9149bc531f52db291940894e90538d466df0e15a95ec3b0ef86eeb3e65064","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T13:57:22Z","title_canon_sha256":"0570fb2bf01b3e335135e8f38954a4c32790e8960468ae9e62e64b26f472ba8b"},"schema_version":"1.0","source":{"id":"2002.06038","kind":"arxiv","version":1}},"canonical_sha256":"e80d495b17540c13892099ea5200f52fae842bda6462992b7a64822776cf301b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e80d495b17540c13892099ea5200f52fae842bda6462992b7a64822776cf301b","first_computed_at":"2026-07-05T00:40:49.417502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:49.417502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uc/0D5Kze4B4nlyW8IQAKR73Zc73+JUHXddmEgwzDRUExCJ1kIIg9R7FklaZRkI0B4f3qNtV5uvwbC2CiR71Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:49.417883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:081f695a8a06d423903248727a7cc4a1272a36174002289fafcf5933c99d665f","sha256:b275acc9af0c3fc86104d9c932765efc9c79b260b3b5be3a4929ffb3df4a39b4"],"state_sha256":"107edf3ff2dbeeae237c17dc6abc1fac5a5bd4b4a6392335e95d7f2f5f74614e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mH3Zk38LF3t+im+vUsAMdzfrkEn8EDzuvr+lKWvOoA8oOWG8KEtpPxcxq5tsAGSC0lRITKUVpP0Jp9DeuN4gCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:18:04.956738Z","bundle_sha256":"6438169c54c101dd7ee4ad7e420f4e1e291200622f152c77f22899b01e5d381e"}}