{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Z36M72SV2KEBQAXFCGAN5BTJG3","short_pith_number":"pith:Z36M72SV","canonical_record":{"source":{"id":"1712.04101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T02:19:25Z","cross_cats_sorted":[],"title_canon_sha256":"9f807db301d3d8b0dfe4aa5e52339b96d5e1b1c2cfe4e7ea596940c2c7c93eea","abstract_canon_sha256":"9927a27d0ca01bbce4cd64d4efd05e8f52b694e0af324fffa31ef3d6ab94488f"},"schema_version":"1.0"},"canonical_sha256":"cefccfea55d2881802e51180de866936dd59e0701df30602c1807d9c7d6bafa3","source":{"kind":"arxiv","id":"1712.04101","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.04101","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"1712.04101v1","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04101","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z36M72SV2KEB","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z36M72SV2KEBQAXF","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z36M72SV","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Z36M72SV2KEBQAXFCGAN5BTJG3","target":"record","payload":{"canonical_record":{"source":{"id":"1712.04101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T02:19:25Z","cross_cats_sorted":[],"title_canon_sha256":"9f807db301d3d8b0dfe4aa5e52339b96d5e1b1c2cfe4e7ea596940c2c7c93eea","abstract_canon_sha256":"9927a27d0ca01bbce4cd64d4efd05e8f52b694e0af324fffa31ef3d6ab94488f"},"schema_version":"1.0"},"canonical_sha256":"cefccfea55d2881802e51180de866936dd59e0701df30602c1807d9c7d6bafa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:09.173390Z","signature_b64":"V5uiCxv40Ci+di5HCmus3TMnHtUfX4+5SPUBU4vG9DUxTFP7lKT6nK+AUguFFWls9JU9eV6RturGGb4ZmqblAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cefccfea55d2881802e51180de866936dd59e0701df30602c1807d9c7d6bafa3","last_reissued_at":"2026-05-18T00:28:09.172820Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:09.172820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.04101","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":"2026-05-18T00:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8VnoMdhcE4iLWovhBeFVxQnpl18Hdw3nDYF74BCXbGcwcOTfVckyjTXoTHwalf7Q6mDD3JUI58QVIJ08qnODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:05:12.832217Z"},"content_sha256":"a7018332032006f913555a48d135345d2533a8ce8a9903150814dd3297a3465c","schema_version":"1.0","event_id":"sha256:a7018332032006f913555a48d135345d2533a8ce8a9903150814dd3297a3465c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Z36M72SV2KEBQAXFCGAN5BTJG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning Boosted by External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nicolas Bougie, Ryutaro Ichise","submitted_at":"2017-12-12T02:19:25Z","abstract_excerpt":"Recent improvements in deep reinforcement learning have allowed to solve problems in many 2D domains such as Atari games. However, in complex 3D environments, numerous learning episodes are required which may be too time consuming or even impossible especially in real-world scenarios. We present a new architecture to combine external knowledge and deep reinforcement learning using only visual input. A key concept of our system is augmenting image input by adding environment feature information and combining two sources of decision. We evaluate the performances of our method in a 3D partially-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04101","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":""},"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":"2026-05-18T00:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5K6ocIYiH9HTPKmMOPEqVK8i3X4p4B3PK1riN30WjIAGjJM4srlc0NgEcGLPQpurY+WwzatX6IA9j76f9cb6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:05:12.832857Z"},"content_sha256":"a7edb57642e202c9482e90a6b1d8e3f7da7f04d3a532e44301989b3cea299f6b","schema_version":"1.0","event_id":"sha256:a7edb57642e202c9482e90a6b1d8e3f7da7f04d3a532e44301989b3cea299f6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/bundle.json","state_url":"https://pith.science/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/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":"2026-05-25T12:05:12Z","links":{"resolver":"https://pith.science/pith/Z36M72SV2KEBQAXFCGAN5BTJG3","bundle":"https://pith.science/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/bundle.json","state":"https://pith.science/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z36M72SV2KEBQAXFCGAN5BTJG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Z36M72SV2KEBQAXFCGAN5BTJG3","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":"9927a27d0ca01bbce4cd64d4efd05e8f52b694e0af324fffa31ef3d6ab94488f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T02:19:25Z","title_canon_sha256":"9f807db301d3d8b0dfe4aa5e52339b96d5e1b1c2cfe4e7ea596940c2c7c93eea"},"schema_version":"1.0","source":{"id":"1712.04101","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.04101","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"1712.04101v1","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04101","created_at":"2026-05-18T00:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z36M72SV2KEB","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z36M72SV2KEBQAXF","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z36M72SV","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:a7edb57642e202c9482e90a6b1d8e3f7da7f04d3a532e44301989b3cea299f6b","target":"graph","created_at":"2026-05-18T00:28:09Z","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"},"paper":{"abstract_excerpt":"Recent improvements in deep reinforcement learning have allowed to solve problems in many 2D domains such as Atari games. However, in complex 3D environments, numerous learning episodes are required which may be too time consuming or even impossible especially in real-world scenarios. We present a new architecture to combine external knowledge and deep reinforcement learning using only visual input. A key concept of our system is augmenting image input by adding environment feature information and combining two sources of decision. We evaluate the performances of our method in a 3D partially-o","authors_text":"Nicolas Bougie, Ryutaro Ichise","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T02:19:25Z","title":"Deep Reinforcement Learning Boosted by External Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04101","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:a7018332032006f913555a48d135345d2533a8ce8a9903150814dd3297a3465c","target":"record","created_at":"2026-05-18T00:28:09Z","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":"9927a27d0ca01bbce4cd64d4efd05e8f52b694e0af324fffa31ef3d6ab94488f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T02:19:25Z","title_canon_sha256":"9f807db301d3d8b0dfe4aa5e52339b96d5e1b1c2cfe4e7ea596940c2c7c93eea"},"schema_version":"1.0","source":{"id":"1712.04101","kind":"arxiv","version":1}},"canonical_sha256":"cefccfea55d2881802e51180de866936dd59e0701df30602c1807d9c7d6bafa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cefccfea55d2881802e51180de866936dd59e0701df30602c1807d9c7d6bafa3","first_computed_at":"2026-05-18T00:28:09.172820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:09.172820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V5uiCxv40Ci+di5HCmus3TMnHtUfX4+5SPUBU4vG9DUxTFP7lKT6nK+AUguFFWls9JU9eV6RturGGb4ZmqblAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:09.173390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.04101","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7018332032006f913555a48d135345d2533a8ce8a9903150814dd3297a3465c","sha256:a7edb57642e202c9482e90a6b1d8e3f7da7f04d3a532e44301989b3cea299f6b"],"state_sha256":"b0b6ddb0626be1915fd51740b6354a706c8b6508b2c997f61f80647680a218ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cR8yaVNvlgKVU51apd2YPliuQmo5jEyaPNF1qZSlqLBu5fAblzDaIy/42eWB9ox1vYxd2zJiNlE1HX603ZX0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T12:05:12.835840Z","bundle_sha256":"303c0f5009dc8a843ef9811bf8beff2c1240b105b3d9415ea4b31e052b554418"}}