{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GIPR6ANFCVPQXWGCQVWR2D227B","short_pith_number":"pith:GIPR6ANF","canonical_record":{"source":{"id":"1810.10593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-24T20:00:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0f254f32b3e973a43166af6ec1232081d5c2256009e1788fb48b88041dec018e","abstract_canon_sha256":"1386910af6486e1fd3fd3cf91339cb2b48ad47c74d5a663e2035010cf39c143e"},"schema_version":"1.0"},"canonical_sha256":"321f1f01a5155f0bd8c2856d1d0f5af86d9805bc2e96480ddb18af6613d59a56","source":{"kind":"arxiv","id":"1810.10593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10593","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10593v1","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10593","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"GIPR6ANFCVPQ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GIPR6ANFCVPQXWGC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GIPR6ANF","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GIPR6ANFCVPQXWGCQVWR2D227B","target":"record","payload":{"canonical_record":{"source":{"id":"1810.10593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-24T20:00:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0f254f32b3e973a43166af6ec1232081d5c2256009e1788fb48b88041dec018e","abstract_canon_sha256":"1386910af6486e1fd3fd3cf91339cb2b48ad47c74d5a663e2035010cf39c143e"},"schema_version":"1.0"},"canonical_sha256":"321f1f01a5155f0bd8c2856d1d0f5af86d9805bc2e96480ddb18af6613d59a56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:20.094703Z","signature_b64":"9PTHRTa6rmgKQfjBjB2nE65eCvrmUzribetUFz0TU1e+KapHaKHuGDOdrrFGyQXZX3h+fyYf36qRpENMYA3bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"321f1f01a5155f0bd8c2856d1d0f5af86d9805bc2e96480ddb18af6613d59a56","last_reissued_at":"2026-05-18T00:02:20.094310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:20.094310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.10593","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":"2026-05-18T00:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdOruQkIce/HicouStdOKpqgk9yBs0/QUszASA1qtNCTPbuEFd3gmahQPgQIYijgj5qkCM3MiFfMHWNGVbwkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:57:35.898919Z"},"content_sha256":"8ac01f5f0e6c46db0326152236d9d1ab890b04ab1e9a7233a73bfb05515bb77e","schema_version":"1.0","event_id":"sha256:8ac01f5f0e6c46db0326152236d9d1ab890b04ab1e9a7233a73bfb05515bb77e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GIPR6ANFCVPQXWGCQVWR2D227B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse reinforcement learning for video games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Tucker, Adam Gleave, Stuart Russell","submitted_at":"2018-10-24T20:00:50Z","abstract_excerpt":"Deep reinforcement learning achieves superhuman performance in a range of video game environments, but requires that a designer manually specify a reward function. It is often easier to provide demonstrations of a target behavior than to design a reward function describing that behavior. Inverse reinforcement learning (IRL) algorithms can infer a reward from demonstrations in low-dimensional continuous control environments, but there has been little work on applying IRL to high-dimensional video games. In our CNN-AIRL baseline, we modify the state-of-the-art adversarial IRL (AIRL) algorithm to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10593","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":"2026-05-18T00:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjcQiNQ0Comv6m5VkDijHxrN8hPGgwOwWwBAPvPikA0FUo+ihTj6ut9eMOygxF+f+jD3QIZkseiKmUHwVsI4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:57:35.899264Z"},"content_sha256":"4eac2b5ee4ff1970d0b218c95ecf8faf2c43cfcaaa1af1c7e16f37e0e174159a","schema_version":"1.0","event_id":"sha256:4eac2b5ee4ff1970d0b218c95ecf8faf2c43cfcaaa1af1c7e16f37e0e174159a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIPR6ANFCVPQXWGCQVWR2D227B/bundle.json","state_url":"https://pith.science/pith/GIPR6ANFCVPQXWGCQVWR2D227B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIPR6ANFCVPQXWGCQVWR2D227B/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":"2026-06-10T19:57:35Z","links":{"resolver":"https://pith.science/pith/GIPR6ANFCVPQXWGCQVWR2D227B","bundle":"https://pith.science/pith/GIPR6ANFCVPQXWGCQVWR2D227B/bundle.json","state":"https://pith.science/pith/GIPR6ANFCVPQXWGCQVWR2D227B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIPR6ANFCVPQXWGCQVWR2D227B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GIPR6ANFCVPQXWGCQVWR2D227B","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":"1386910af6486e1fd3fd3cf91339cb2b48ad47c74d5a663e2035010cf39c143e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-24T20:00:50Z","title_canon_sha256":"0f254f32b3e973a43166af6ec1232081d5c2256009e1788fb48b88041dec018e"},"schema_version":"1.0","source":{"id":"1810.10593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10593","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10593v1","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10593","created_at":"2026-05-18T00:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"GIPR6ANFCVPQ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GIPR6ANFCVPQXWGC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GIPR6ANF","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:4eac2b5ee4ff1970d0b218c95ecf8faf2c43cfcaaa1af1c7e16f37e0e174159a","target":"graph","created_at":"2026-05-18T00:02:20Z","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":"Deep reinforcement learning achieves superhuman performance in a range of video game environments, but requires that a designer manually specify a reward function. It is often easier to provide demonstrations of a target behavior than to design a reward function describing that behavior. Inverse reinforcement learning (IRL) algorithms can infer a reward from demonstrations in low-dimensional continuous control environments, but there has been little work on applying IRL to high-dimensional video games. In our CNN-AIRL baseline, we modify the state-of-the-art adversarial IRL (AIRL) algorithm to","authors_text":"Aaron Tucker, Adam Gleave, Stuart Russell","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-24T20:00:50Z","title":"Inverse reinforcement learning for video games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10593","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":"sha256:8ac01f5f0e6c46db0326152236d9d1ab890b04ab1e9a7233a73bfb05515bb77e","target":"record","created_at":"2026-05-18T00:02:20Z","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":"1386910af6486e1fd3fd3cf91339cb2b48ad47c74d5a663e2035010cf39c143e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-24T20:00:50Z","title_canon_sha256":"0f254f32b3e973a43166af6ec1232081d5c2256009e1788fb48b88041dec018e"},"schema_version":"1.0","source":{"id":"1810.10593","kind":"arxiv","version":1}},"canonical_sha256":"321f1f01a5155f0bd8c2856d1d0f5af86d9805bc2e96480ddb18af6613d59a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"321f1f01a5155f0bd8c2856d1d0f5af86d9805bc2e96480ddb18af6613d59a56","first_computed_at":"2026-05-18T00:02:20.094310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:20.094310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9PTHRTa6rmgKQfjBjB2nE65eCvrmUzribetUFz0TU1e+KapHaKHuGDOdrrFGyQXZX3h+fyYf36qRpENMYA3bDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:20.094703Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.10593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ac01f5f0e6c46db0326152236d9d1ab890b04ab1e9a7233a73bfb05515bb77e","sha256:4eac2b5ee4ff1970d0b218c95ecf8faf2c43cfcaaa1af1c7e16f37e0e174159a"],"state_sha256":"c4920aa885e4f61621e1ee0951957c7da8de5893761e1b222ab5372411ff94fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxW9OYAWvNb8Q4457HUiKjco1S5lw21YVjv81CgRVZhGJVng2aOHx//6LC4Ka0xvdpN+E7xNLJDpO31JJPY5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T19:57:35.901163Z","bundle_sha256":"fc8371ab0c930b290843055d54654985e4a173147d0e05893ef5ab7cd8614f0e"}}