{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZOVO66372KDJ2ATYRIH4RO63YA","short_pith_number":"pith:ZOVO6637","canonical_record":{"source":{"id":"2006.15061","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T15:39:40Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"244165524e51dea8e5552ea982fe4bd473917b2b3f0a5b44bc7e0a6d3d1dd002","abstract_canon_sha256":"2c269c01130ff4e24303210630584074c437aa72ae2eb92d644bcb049b9402d6"},"schema_version":"1.0"},"canonical_sha256":"cbaaef7b7fd2869d02788a0fc8bbdbc01a5fe6e518f59efbbaf598969f7441dd","source":{"kind":"arxiv","id":"2006.15061","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15061","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15061v4","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15061","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZOVO66372KDJ","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZOVO66372KDJ2ATY","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZOVO6637","created_at":"2026-07-05T01:34:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZOVO66372KDJ2ATYRIH4RO63YA","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15061","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T15:39:40Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"244165524e51dea8e5552ea982fe4bd473917b2b3f0a5b44bc7e0a6d3d1dd002","abstract_canon_sha256":"2c269c01130ff4e24303210630584074c437aa72ae2eb92d644bcb049b9402d6"},"schema_version":"1.0"},"canonical_sha256":"cbaaef7b7fd2869d02788a0fc8bbdbc01a5fe6e518f59efbbaf598969f7441dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:43.379283Z","signature_b64":"Ml2RrX+bMszl3Sa7oZLVxCg59HGL22hFaeh6brwx4QjiAjK1+tMAo+YswqZ4VDKW3/b4XxfnXF3ekdWy/bgcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbaaef7b7fd2869d02788a0fc8bbdbc01a5fe6e518f59efbbaf598969f7441dd","last_reissued_at":"2026-07-05T01:34:43.378900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:43.378900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15061","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7NNwGSp1J/zupCOKr7S7L3XqQdqBTTZoXrVm5szBq48+NtOHuJ6Z93pXV/d8Miw+KcGj1e41qIYeykqbf2YBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:08:28.708476Z"},"content_sha256":"7a755535f2892e015529e7a3f835aa1cc9ffa7ca2e1964edd8acf77433483ccb","schema_version":"1.0","event_id":"sha256:7a755535f2892e015529e7a3f835aa1cc9ffa7ca2e1964edd8acf77433483ccb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZOVO66372KDJ2ATYRIH4RO63YA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intrinsic Reward Driven Imitation Learning via Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ivor W. Tsang, Xingrui Yu, Yueming Lyu","submitted_at":"2020-06-26T15:39:40Z","abstract_excerpt":"Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this challenge, we propose a novel reward learning module to generate intrinsic reward signals via a generative model. Our generative method can perform better forward state transition and backward action encoding, which improves the module's dynamics modeling ability in the environment. Thus, our module provides the imitation agent both the intrinsic intention of the dem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15061","kind":"arxiv","version":4},"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/2006.15061/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":"2026-07-05T01:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQlBb7hlBv5NCYdFrYOR7Yfz8l7hj69rr5Vgdb0P9dpWWMS04BcajsEXICzPW6KD93BvO4MvzprjvOoehxJ+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:08:28.708854Z"},"content_sha256":"5e171a391484e1dcfeccaecf7f09474a4e404275f7e68ca4cafee1252e3811e6","schema_version":"1.0","event_id":"sha256:5e171a391484e1dcfeccaecf7f09474a4e404275f7e68ca4cafee1252e3811e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOVO66372KDJ2ATYRIH4RO63YA/bundle.json","state_url":"https://pith.science/pith/ZOVO66372KDJ2ATYRIH4RO63YA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOVO66372KDJ2ATYRIH4RO63YA/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":"2026-07-11T18:08:28Z","links":{"resolver":"https://pith.science/pith/ZOVO66372KDJ2ATYRIH4RO63YA","bundle":"https://pith.science/pith/ZOVO66372KDJ2ATYRIH4RO63YA/bundle.json","state":"https://pith.science/pith/ZOVO66372KDJ2ATYRIH4RO63YA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOVO66372KDJ2ATYRIH4RO63YA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZOVO66372KDJ2ATYRIH4RO63YA","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":"2c269c01130ff4e24303210630584074c437aa72ae2eb92d644bcb049b9402d6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T15:39:40Z","title_canon_sha256":"244165524e51dea8e5552ea982fe4bd473917b2b3f0a5b44bc7e0a6d3d1dd002"},"schema_version":"1.0","source":{"id":"2006.15061","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15061","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15061v4","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15061","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZOVO66372KDJ","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZOVO66372KDJ2ATY","created_at":"2026-07-05T01:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZOVO6637","created_at":"2026-07-05T01:34:43Z"}],"graph_snapshots":[{"event_id":"sha256:5e171a391484e1dcfeccaecf7f09474a4e404275f7e68ca4cafee1252e3811e6","target":"graph","created_at":"2026-07-05T01:34:43Z","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/2006.15061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this challenge, we propose a novel reward learning module to generate intrinsic reward signals via a generative model. Our generative method can perform better forward state transition and backward action encoding, which improves the module's dynamics modeling ability in the environment. Thus, our module provides the imitation agent both the intrinsic intention of the dem","authors_text":"Ivor W. Tsang, Xingrui Yu, Yueming Lyu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T15:39:40Z","title":"Intrinsic Reward Driven Imitation Learning via Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15061","kind":"arxiv","version":4},"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":"sha256:7a755535f2892e015529e7a3f835aa1cc9ffa7ca2e1964edd8acf77433483ccb","target":"record","created_at":"2026-07-05T01:34:43Z","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":"2c269c01130ff4e24303210630584074c437aa72ae2eb92d644bcb049b9402d6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T15:39:40Z","title_canon_sha256":"244165524e51dea8e5552ea982fe4bd473917b2b3f0a5b44bc7e0a6d3d1dd002"},"schema_version":"1.0","source":{"id":"2006.15061","kind":"arxiv","version":4}},"canonical_sha256":"cbaaef7b7fd2869d02788a0fc8bbdbc01a5fe6e518f59efbbaf598969f7441dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbaaef7b7fd2869d02788a0fc8bbdbc01a5fe6e518f59efbbaf598969f7441dd","first_computed_at":"2026-07-05T01:34:43.378900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:43.378900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ml2RrX+bMszl3Sa7oZLVxCg59HGL22hFaeh6brwx4QjiAjK1+tMAo+YswqZ4VDKW3/b4XxfnXF3ekdWy/bgcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:43.379283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15061","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a755535f2892e015529e7a3f835aa1cc9ffa7ca2e1964edd8acf77433483ccb","sha256:5e171a391484e1dcfeccaecf7f09474a4e404275f7e68ca4cafee1252e3811e6"],"state_sha256":"195288945750efd928b2d980f3140260124ae3cbff6b0b96afb62a170888e8e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+KJDnxDPjrUt+Qxl0tIRB5gBY3uzFXeTHfFvIUM9n5iB347RUFLazizLjB6FSqQ6fZ1glWdMDuM5dQz76a57AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T18:08:28.711003Z","bundle_sha256":"e22d851a6bb5bb42be6e0af60a742502c99ef3d13fb4230c291d98b7d94a66a7"}}