{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JYP7Q74OMPKILD2EP2D3ZDEY6E","short_pith_number":"pith:JYP7Q74O","canonical_record":{"source":{"id":"2010.03956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T03:43:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22fea8044b75ae7688cb5df284b1ef88f419343f46358c3f4969eb096d57ce88","abstract_canon_sha256":"680a6fac58da127402983352d7fa99441b305da98c06fadd7b59acf5bb434699"},"schema_version":"1.0"},"canonical_sha256":"4e1ff87f8e63d4858f447e87bc8c98f12e9e85f7485c1a1aa92066cef0a8cd07","source":{"kind":"arxiv","id":"2010.03956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03956","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03956v1","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03956","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_12","alias_value":"JYP7Q74OMPKI","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_16","alias_value":"JYP7Q74OMPKILD2E","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_8","alias_value":"JYP7Q74O","created_at":"2026-07-05T01:41:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JYP7Q74OMPKILD2EP2D3ZDEY6E","target":"record","payload":{"canonical_record":{"source":{"id":"2010.03956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T03:43:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22fea8044b75ae7688cb5df284b1ef88f419343f46358c3f4969eb096d57ce88","abstract_canon_sha256":"680a6fac58da127402983352d7fa99441b305da98c06fadd7b59acf5bb434699"},"schema_version":"1.0"},"canonical_sha256":"4e1ff87f8e63d4858f447e87bc8c98f12e9e85f7485c1a1aa92066cef0a8cd07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:25.465352Z","signature_b64":"4MAcQcIadJ7jJhCTVpAjlRIMDmXgdWTkYgKTHlE2ukECRsag8f4v5KTQPql4C1AnPChGEHkNZmMYrdle7mspAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e1ff87f8e63d4858f447e87bc8c98f12e9e85f7485c1a1aa92066cef0a8cd07","last_reissued_at":"2026-07-05T01:41:25.464883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:25.464883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.03956","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":"2026-07-05T01:41:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nn7s0nhH1QuAV9FjvgDz0d3KJiyrE7/oDxlzFzStpDAUMxF+m2ApPRtvdniIuFfOu5j0zZz3R6CwF0Ve+snBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:47:03.939496Z"},"content_sha256":"c976e5277f5703ec766b2a286aa81ad9eb34e81098ec67000036d40d7b606437","schema_version":"1.0","event_id":"sha256:c976e5277f5703ec766b2a286aa81ad9eb34e81098ec67000036d40d7b606437"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JYP7Q74OMPKILD2EP2D3ZDEY6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Santiago Onta\\~n\\'on, Shengyi Huang","submitted_at":"2020-10-05T03:43:06Z","abstract_excerpt":"Training agents using Reinforcement Learning in games with sparse rewards is a challenging problem, since large amounts of exploration are required to retrieve even the first reward. To tackle this problem, a common approach is to use reward shaping to help exploration. However, an important drawback of reward shaping is that agents sometimes learn to optimize the shaped reward instead of the true objective. In this paper, we present a novel technique that we call action guidance that successfully trains agents to eventually optimize the true objective in games with sparse rewards while mainta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03956","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/2010.03956/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":"2026-07-05T01:41:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qYyblVhgQalbBXgF4wP6z2gJL0ZaJEWU9epzKKYvQM3/Te5wpeC+ffQo8n/0KKqGdW7VsqpNRBkoqKTxa7V6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:47:03.940012Z"},"content_sha256":"70835430ebf08cdfcbd29ea7b40c6de3ce98bb87194f20d01a0a7ece7b800e80","schema_version":"1.0","event_id":"sha256:70835430ebf08cdfcbd29ea7b40c6de3ce98bb87194f20d01a0a7ece7b800e80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/bundle.json","state_url":"https://pith.science/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/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":"2026-08-18T06:47:03Z","links":{"resolver":"https://pith.science/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E","bundle":"https://pith.science/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/bundle.json","state":"https://pith.science/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JYP7Q74OMPKILD2EP2D3ZDEY6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JYP7Q74OMPKILD2EP2D3ZDEY6E","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":"680a6fac58da127402983352d7fa99441b305da98c06fadd7b59acf5bb434699","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T03:43:06Z","title_canon_sha256":"22fea8044b75ae7688cb5df284b1ef88f419343f46358c3f4969eb096d57ce88"},"schema_version":"1.0","source":{"id":"2010.03956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03956","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03956v1","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03956","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_12","alias_value":"JYP7Q74OMPKI","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_16","alias_value":"JYP7Q74OMPKILD2E","created_at":"2026-07-05T01:41:25Z"},{"alias_kind":"pith_short_8","alias_value":"JYP7Q74O","created_at":"2026-07-05T01:41:25Z"}],"graph_snapshots":[{"event_id":"sha256:70835430ebf08cdfcbd29ea7b40c6de3ce98bb87194f20d01a0a7ece7b800e80","target":"graph","created_at":"2026-07-05T01:41:25Z","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/2010.03956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training agents using Reinforcement Learning in games with sparse rewards is a challenging problem, since large amounts of exploration are required to retrieve even the first reward. To tackle this problem, a common approach is to use reward shaping to help exploration. However, an important drawback of reward shaping is that agents sometimes learn to optimize the shaped reward instead of the true objective. In this paper, we present a novel technique that we call action guidance that successfully trains agents to eventually optimize the true objective in games with sparse rewards while mainta","authors_text":"Santiago Onta\\~n\\'on, Shengyi Huang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T03:43:06Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03956","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:c976e5277f5703ec766b2a286aa81ad9eb34e81098ec67000036d40d7b606437","target":"record","created_at":"2026-07-05T01:41:25Z","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":"680a6fac58da127402983352d7fa99441b305da98c06fadd7b59acf5bb434699","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T03:43:06Z","title_canon_sha256":"22fea8044b75ae7688cb5df284b1ef88f419343f46358c3f4969eb096d57ce88"},"schema_version":"1.0","source":{"id":"2010.03956","kind":"arxiv","version":1}},"canonical_sha256":"4e1ff87f8e63d4858f447e87bc8c98f12e9e85f7485c1a1aa92066cef0a8cd07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e1ff87f8e63d4858f447e87bc8c98f12e9e85f7485c1a1aa92066cef0a8cd07","first_computed_at":"2026-07-05T01:41:25.464883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:25.464883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4MAcQcIadJ7jJhCTVpAjlRIMDmXgdWTkYgKTHlE2ukECRsag8f4v5KTQPql4C1AnPChGEHkNZmMYrdle7mspAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:25.465352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c976e5277f5703ec766b2a286aa81ad9eb34e81098ec67000036d40d7b606437","sha256:70835430ebf08cdfcbd29ea7b40c6de3ce98bb87194f20d01a0a7ece7b800e80"],"state_sha256":"12a53900047508aa4911bbf51c22cd576b5c65fbbef627656af9153949e4c9d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKs+Ms/xko4OMflkbZroh6R3KJj//yCn49NxpoRjDHeakqaXD71s8bsf8edgOMdiFhPaCv871W0QKkWFLVIUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:47:03.943946Z","bundle_sha256":"8f59b90c3b5bf7237a064cd0e06296d25f8644299a9a3e316bf193d89d2bca7b"}}