{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:B3S7UVX4YJQA2Z6HZCDZWRU7WW","short_pith_number":"pith:B3S7UVX4","canonical_record":{"source":{"id":"2102.10330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T12:40:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d2b1881ce66b8b3308cbdb5113993eb82eb3672358e34a35b598e7cf91779bc","abstract_canon_sha256":"599fe56fac5cd401f5e3a226002c18117955582c891a6a41303f584aae0d1ba8"},"schema_version":"1.0"},"canonical_sha256":"0ee5fa56fcc2600d67c7c8879b469fb5ab7248e7fae7441cbad69e3085b8327c","source":{"kind":"arxiv","id":"2102.10330","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10330","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10330v2","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10330","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"B3S7UVX4YJQA","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_16","alias_value":"B3S7UVX4YJQA2Z6H","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_8","alias_value":"B3S7UVX4","created_at":"2026-07-05T02:49:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:B3S7UVX4YJQA2Z6HZCDZWRU7WW","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T12:40:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d2b1881ce66b8b3308cbdb5113993eb82eb3672358e34a35b598e7cf91779bc","abstract_canon_sha256":"599fe56fac5cd401f5e3a226002c18117955582c891a6a41303f584aae0d1ba8"},"schema_version":"1.0"},"canonical_sha256":"0ee5fa56fcc2600d67c7c8879b469fb5ab7248e7fae7441cbad69e3085b8327c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:25.428272Z","signature_b64":"aYcKNUinMamVaalFFhayB6Rkeqy4px2D0iXUngqy8SBzadIdWSYxWHFI3Otn5RoBTKlZvO6vci7gCcBeYNuTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee5fa56fcc2600d67c7c8879b469fb5ab7248e7fae7441cbad69e3085b8327c","last_reissued_at":"2026-07-05T02:49:25.427812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:25.427812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10330","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":"2026-07-05T02:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8utGN25N+bS+O+AiUPJG3bwJh8tdID3pMKILZztrwtcGOlgrIzZh7ljz06aHocFBmkv/LXTYNDuodOPQiKMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:55:44.566607Z"},"content_sha256":"ce05a959036e86918d66f4ed18efd12cb16e8ec8d95c9ad7a944cf64d5c36661","schema_version":"1.0","event_id":"sha256:ce05a959036e86918d66f4ed18efd12cb16e8ec8d95c9ad7a944cf64d5c36661"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:B3S7UVX4YJQA2Z6HZCDZWRU7WW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Roberta Raileanu, Rob Fergus","submitted_at":"2021-02-20T12:40:11Z","abstract_excerpt":"Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value function than to learn the optimal policy. Consequently, the use of a shared representation for the policy and value function can lead to overfitting. To alleviate this problem, we propose two approaches which are combined to create IDAAC: Invariant Decoupled Advantage Actor-Critic. First, IDAAC decouples the optimization of the policy and value function, u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10330","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/2102.10330/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":"2026-07-05T02:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0clAOQz+It2JCj7FwJ+LuaGXYe61TXF3bQKQ/pyn4PZR0JwN9iMth5Dej0o+sQVtmFIi5eBLT/LzRvjIOZd0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:55:44.567119Z"},"content_sha256":"055089e4d353f406a268cd5ae0aae33932ccdf54adfff5163838215d07a20169","schema_version":"1.0","event_id":"sha256:055089e4d353f406a268cd5ae0aae33932ccdf54adfff5163838215d07a20169"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/bundle.json","state_url":"https://pith.science/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/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":"2026-08-11T13:55:44Z","links":{"resolver":"https://pith.science/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW","bundle":"https://pith.science/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/bundle.json","state":"https://pith.science/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3S7UVX4YJQA2Z6HZCDZWRU7WW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B3S7UVX4YJQA2Z6HZCDZWRU7WW","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":"599fe56fac5cd401f5e3a226002c18117955582c891a6a41303f584aae0d1ba8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T12:40:11Z","title_canon_sha256":"0d2b1881ce66b8b3308cbdb5113993eb82eb3672358e34a35b598e7cf91779bc"},"schema_version":"1.0","source":{"id":"2102.10330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10330","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10330v2","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10330","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"B3S7UVX4YJQA","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_16","alias_value":"B3S7UVX4YJQA2Z6H","created_at":"2026-07-05T02:49:25Z"},{"alias_kind":"pith_short_8","alias_value":"B3S7UVX4","created_at":"2026-07-05T02:49:25Z"}],"graph_snapshots":[{"event_id":"sha256:055089e4d353f406a268cd5ae0aae33932ccdf54adfff5163838215d07a20169","target":"graph","created_at":"2026-07-05T02:49:25Z","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/2102.10330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value function than to learn the optimal policy. Consequently, the use of a shared representation for the policy and value function can lead to overfitting. To alleviate this problem, we propose two approaches which are combined to create IDAAC: Invariant Decoupled Advantage Actor-Critic. First, IDAAC decouples the optimization of the policy and value function, u","authors_text":"Roberta Raileanu, Rob Fergus","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T12:40:11Z","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10330","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:ce05a959036e86918d66f4ed18efd12cb16e8ec8d95c9ad7a944cf64d5c36661","target":"record","created_at":"2026-07-05T02:49:25Z","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":"599fe56fac5cd401f5e3a226002c18117955582c891a6a41303f584aae0d1ba8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T12:40:11Z","title_canon_sha256":"0d2b1881ce66b8b3308cbdb5113993eb82eb3672358e34a35b598e7cf91779bc"},"schema_version":"1.0","source":{"id":"2102.10330","kind":"arxiv","version":2}},"canonical_sha256":"0ee5fa56fcc2600d67c7c8879b469fb5ab7248e7fae7441cbad69e3085b8327c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ee5fa56fcc2600d67c7c8879b469fb5ab7248e7fae7441cbad69e3085b8327c","first_computed_at":"2026-07-05T02:49:25.427812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:25.427812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aYcKNUinMamVaalFFhayB6Rkeqy4px2D0iXUngqy8SBzadIdWSYxWHFI3Otn5RoBTKlZvO6vci7gCcBeYNuTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:25.428272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce05a959036e86918d66f4ed18efd12cb16e8ec8d95c9ad7a944cf64d5c36661","sha256:055089e4d353f406a268cd5ae0aae33932ccdf54adfff5163838215d07a20169"],"state_sha256":"6070720234f7ca410d42a615ba612f89591c20162b6d736acae685c39b7dc869"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crfg9o88MBTy8z0v0cpYad08ibskn3yJ/QFRkE+X8qlHJ9DK2yrTu/heAFCIhQoQUkZ7zPxO5Gl7y2mTAgy+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:55:44.572333Z","bundle_sha256":"c85d2242f607b7048b5bd4e7d160e0b46032a4b3f9f54365fbe630c158877187"}}