{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O7E3ZJTRRL6SA7BI5CGV7SYMQN","short_pith_number":"pith:O7E3ZJTR","canonical_record":{"source":{"id":"2002.01963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-05T19:21:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ebd96f3c653f87b845202baab3e11c2c24f808923c239828ee777859d9bd66bd","abstract_canon_sha256":"62e25b7b6fd6cf4723ef4653b4e55aa95889d158476aa0269625e28e76f454a7"},"schema_version":"1.0"},"canonical_sha256":"77c9bca6718afd207c28e88d5fcb0c834e428e445b419d0a614b898495016e23","source":{"kind":"arxiv","id":"2002.01963","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01963","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01963v2","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01963","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"O7E3ZJTRRL6S","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"O7E3ZJTRRL6SA7BI","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"O7E3ZJTR","created_at":"2026-07-05T01:09:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O7E3ZJTRRL6SA7BI5CGV7SYMQN","target":"record","payload":{"canonical_record":{"source":{"id":"2002.01963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-05T19:21:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ebd96f3c653f87b845202baab3e11c2c24f808923c239828ee777859d9bd66bd","abstract_canon_sha256":"62e25b7b6fd6cf4723ef4653b4e55aa95889d158476aa0269625e28e76f454a7"},"schema_version":"1.0"},"canonical_sha256":"77c9bca6718afd207c28e88d5fcb0c834e428e445b419d0a614b898495016e23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:57.784051Z","signature_b64":"mcXFqeE+Q/U60/EUW0Bl3E2rE+2Kuduhl9jYe8zOrJJSVNGPHGUFDrBAX/bsmoysbz0LCrpxkkHJL+qE1A6wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77c9bca6718afd207c28e88d5fcb0c834e428e445b419d0a614b898495016e23","last_reissued_at":"2026-07-05T01:09:57.783564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:57.783564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.01963","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUl5qWTuvF+ShVJ7sCGWmqzWWQ1zYxfj6Dranvmx4jr6lspK0fMs/QSkoGW6f3F2vr/uaSXHCy6nHSxULdZnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:33:50.050177Z"},"content_sha256":"615338504db0e60134219721f39c086ca01b0a04c2860784eefdf564acd1b222","schema_version":"1.0","event_id":"sha256:615338504db0e60134219721f39c086ca01b0a04c2860784eefdf564acd1b222"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O7E3ZJTRRL6SA7BI5CGV7SYMQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Rui Zhao, Volker Tresp, Wei Xu, Yang Gao","submitted_at":"2020-02-05T19:21:20Z","abstract_excerpt":"In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01963","kind":"arxiv","version":2},"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/2002.01963/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":"2026-07-05T01:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmPt/9xatFK1BGWuJgqFmDFHl6bnYx5CBWgH8P4QGDm9GtsMxYZRIyI1yRTI1n8F6wR59uuoJcJEKNEtr9NyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:33:50.050703Z"},"content_sha256":"f0c0510a3453eecbbbc9c2d3063a34e0478e05abe6bb3d5d63b4f4498be8b7f4","schema_version":"1.0","event_id":"sha256:f0c0510a3453eecbbbc9c2d3063a34e0478e05abe6bb3d5d63b4f4498be8b7f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/bundle.json","state_url":"https://pith.science/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/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":"2026-08-14T13:33:50Z","links":{"resolver":"https://pith.science/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN","bundle":"https://pith.science/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/bundle.json","state":"https://pith.science/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7E3ZJTRRL6SA7BI5CGV7SYMQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O7E3ZJTRRL6SA7BI5CGV7SYMQN","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":"62e25b7b6fd6cf4723ef4653b4e55aa95889d158476aa0269625e28e76f454a7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-05T19:21:20Z","title_canon_sha256":"ebd96f3c653f87b845202baab3e11c2c24f808923c239828ee777859d9bd66bd"},"schema_version":"1.0","source":{"id":"2002.01963","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01963","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01963v2","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01963","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"O7E3ZJTRRL6S","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"O7E3ZJTRRL6SA7BI","created_at":"2026-07-05T01:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"O7E3ZJTR","created_at":"2026-07-05T01:09:57Z"}],"graph_snapshots":[{"event_id":"sha256:f0c0510a3453eecbbbc9c2d3063a34e0478e05abe6bb3d5d63b4f4498be8b7f4","target":"graph","created_at":"2026-07-05T01:09:57Z","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/2002.01963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized eff","authors_text":"Pieter Abbeel, Rui Zhao, Volker Tresp, Wei Xu, Yang Gao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-05T19:21:20Z","title":"Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01963","kind":"arxiv","version":2},"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":"sha256:615338504db0e60134219721f39c086ca01b0a04c2860784eefdf564acd1b222","target":"record","created_at":"2026-07-05T01:09:57Z","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":"62e25b7b6fd6cf4723ef4653b4e55aa95889d158476aa0269625e28e76f454a7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-05T19:21:20Z","title_canon_sha256":"ebd96f3c653f87b845202baab3e11c2c24f808923c239828ee777859d9bd66bd"},"schema_version":"1.0","source":{"id":"2002.01963","kind":"arxiv","version":2}},"canonical_sha256":"77c9bca6718afd207c28e88d5fcb0c834e428e445b419d0a614b898495016e23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77c9bca6718afd207c28e88d5fcb0c834e428e445b419d0a614b898495016e23","first_computed_at":"2026-07-05T01:09:57.783564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:57.783564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcXFqeE+Q/U60/EUW0Bl3E2rE+2Kuduhl9jYe8zOrJJSVNGPHGUFDrBAX/bsmoysbz0LCrpxkkHJL+qE1A6wDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:57.784051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.01963","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:615338504db0e60134219721f39c086ca01b0a04c2860784eefdf564acd1b222","sha256:f0c0510a3453eecbbbc9c2d3063a34e0478e05abe6bb3d5d63b4f4498be8b7f4"],"state_sha256":"c75627ecba7fba4cccd9c4becb9a0cc74457f868571dcecb59494d9c0abd1cd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PuSBrXVVacuFecgJF6jBaeWOgfLganc9LTtykLidLRmkyCoHbUauhUIB9MZ//OA4eMxOlUyWHbAgwVoD0wjDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:33:50.054773Z","bundle_sha256":"94049437777d24fdfcd87f192c7b093980de795f18fe7c4fc1f4abcd3da2517a"}}