{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LAJ37YKSHKS6JY3XJWAKSZV3IX","short_pith_number":"pith:LAJ37YKS","canonical_record":{"source":{"id":"2306.10216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-17T00:25:58Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"28481c824966b9b3b8c107b535ecfa217dd818f08d55c1db3407f94412b9ccf6","abstract_canon_sha256":"e65c6977b1eaf7db2a12bd52205edba4e1c772045bfb92e77f6c586b63f395fe"},"schema_version":"1.0"},"canonical_sha256":"5813bfe1523aa5e4e3774d80a966bb45fc508fe00575afe8e14fe148f21e631d","source":{"kind":"arxiv","id":"2306.10216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10216","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10216v1","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10216","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"LAJ37YKSHKS6","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"LAJ37YKSHKS6JY3X","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"LAJ37YKS","created_at":"2026-07-05T08:13:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LAJ37YKSHKS6JY3XJWAKSZV3IX","target":"record","payload":{"canonical_record":{"source":{"id":"2306.10216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-17T00:25:58Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"28481c824966b9b3b8c107b535ecfa217dd818f08d55c1db3407f94412b9ccf6","abstract_canon_sha256":"e65c6977b1eaf7db2a12bd52205edba4e1c772045bfb92e77f6c586b63f395fe"},"schema_version":"1.0"},"canonical_sha256":"5813bfe1523aa5e4e3774d80a966bb45fc508fe00575afe8e14fe148f21e631d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:59.284573Z","signature_b64":"CN0DYI/Pf9gXTP0tEp3D1HU0qk6LAYk4z7n9HqkmlQJF6hNx7+fxGY5hOKmbZ8zdSEnpn5a74IFkOtSB9pDfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5813bfe1523aa5e4e3774d80a966bb45fc508fe00575afe8e14fe148f21e631d","last_reissued_at":"2026-07-05T08:13:59.284156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:59.284156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.10216","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":"2026-07-05T08:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGO9oxnU8wdFPo+Ye2Lcg9C8cD6t0vDuTt1QNcWUmzEVlo+NkON3eJczqXo12gU6jWQeoIRuNzWH3MAnTjvXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:27:54.694958Z"},"content_sha256":"f6898405752cf113a985aa1432008ad392f6d2f10cdea819dcc13985f46e2f31","schema_version":"1.0","event_id":"sha256:f6898405752cf113a985aa1432008ad392f6d2f10cdea819dcc13985f46e2f31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LAJ37YKSHKS6JY3XJWAKSZV3IX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vanishing Bias Heuristic-guided Reinforcement Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao Xiang, Qinru Li","submitted_at":"2023-06-17T00:25:58Z","abstract_excerpt":"Reinforcement Learning has achieved tremendous success in the many Atari games. In this paper we explored with the lunar lander environment and implemented classical methods including Q-Learning, SARSA, MC as well as tiling coding. We also implemented Neural Network based methods including DQN, Double DQN, Clipped DQN. On top of these, we proposed a new algorithm called Heuristic RL which utilizes heuristic to guide the early stage training while alleviating the introduced human bias. Our experiments showed promising results for our proposed methods in the lunar lander environment."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10216","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/2306.10216/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":"2026-07-05T08:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFzSsYT04xWgKM3Tq0GxTPnfu7YIUTZRty9M/fG0HlZFZxfS0JyxYctNIbM4Kd2e6A82Mz84pDVG4mUDpVzsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:27:54.695478Z"},"content_sha256":"fd164cbe4ca6ed548178af486ad990eac19fe7c009176801fa1a60f1097c74e5","schema_version":"1.0","event_id":"sha256:fd164cbe4ca6ed548178af486ad990eac19fe7c009176801fa1a60f1097c74e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/bundle.json","state_url":"https://pith.science/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/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":"2026-08-23T15:27:54Z","links":{"resolver":"https://pith.science/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX","bundle":"https://pith.science/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/bundle.json","state":"https://pith.science/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LAJ37YKSHKS6JY3XJWAKSZV3IX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LAJ37YKSHKS6JY3XJWAKSZV3IX","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":"e65c6977b1eaf7db2a12bd52205edba4e1c772045bfb92e77f6c586b63f395fe","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-17T00:25:58Z","title_canon_sha256":"28481c824966b9b3b8c107b535ecfa217dd818f08d55c1db3407f94412b9ccf6"},"schema_version":"1.0","source":{"id":"2306.10216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10216","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10216v1","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10216","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"LAJ37YKSHKS6","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"LAJ37YKSHKS6JY3X","created_at":"2026-07-05T08:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"LAJ37YKS","created_at":"2026-07-05T08:13:59Z"}],"graph_snapshots":[{"event_id":"sha256:fd164cbe4ca6ed548178af486ad990eac19fe7c009176801fa1a60f1097c74e5","target":"graph","created_at":"2026-07-05T08:13:59Z","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/2306.10216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning has achieved tremendous success in the many Atari games. In this paper we explored with the lunar lander environment and implemented classical methods including Q-Learning, SARSA, MC as well as tiling coding. We also implemented Neural Network based methods including DQN, Double DQN, Clipped DQN. On top of these, we proposed a new algorithm called Heuristic RL which utilizes heuristic to guide the early stage training while alleviating the introduced human bias. Our experiments showed promising results for our proposed methods in the lunar lander environment.","authors_text":"Hao Xiang, Qinru Li","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-17T00:25:58Z","title":"Vanishing Bias Heuristic-guided Reinforcement Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10216","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:f6898405752cf113a985aa1432008ad392f6d2f10cdea819dcc13985f46e2f31","target":"record","created_at":"2026-07-05T08:13:59Z","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":"e65c6977b1eaf7db2a12bd52205edba4e1c772045bfb92e77f6c586b63f395fe","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-17T00:25:58Z","title_canon_sha256":"28481c824966b9b3b8c107b535ecfa217dd818f08d55c1db3407f94412b9ccf6"},"schema_version":"1.0","source":{"id":"2306.10216","kind":"arxiv","version":1}},"canonical_sha256":"5813bfe1523aa5e4e3774d80a966bb45fc508fe00575afe8e14fe148f21e631d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5813bfe1523aa5e4e3774d80a966bb45fc508fe00575afe8e14fe148f21e631d","first_computed_at":"2026-07-05T08:13:59.284156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:59.284156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CN0DYI/Pf9gXTP0tEp3D1HU0qk6LAYk4z7n9HqkmlQJF6hNx7+fxGY5hOKmbZ8zdSEnpn5a74IFkOtSB9pDfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:59.284573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6898405752cf113a985aa1432008ad392f6d2f10cdea819dcc13985f46e2f31","sha256:fd164cbe4ca6ed548178af486ad990eac19fe7c009176801fa1a60f1097c74e5"],"state_sha256":"c4cc39127e32206b2d43ba7f28a62aa1b452c92f46e84a8e15fb86d716b66b50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XIGIQMvQ4Eo9BnaQFa6N3fWI/7Yi5dMY8g/KAtt2dT5n0hLLEw/zpwd9yMOl9k40l1ovfIvEzODGFDjSyInmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:27:54.700091Z","bundle_sha256":"004386c360c571ff4778a639bd6a84ce77356ccbe903258a20d11689e46e2920"}}