{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IVH46KBHI2QNUUA6JGXQLCFZEU","short_pith_number":"pith:IVH46KBH","canonical_record":{"source":{"id":"2506.01639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T13:15:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17b759786343f7692f990afe1c66a6cd69a7174831f36064872915939e323e71","abstract_canon_sha256":"1aaed248e096ccf6486bedddbb36c8f08443737facbaac19b688d22eba072f23"},"schema_version":"1.0"},"canonical_sha256":"454fcf282746a0da501e49af0588b9253cd977a5553f4498bf915d4e2906ff80","source":{"kind":"arxiv","id":"2506.01639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01639","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01639v1","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01639","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"IVH46KBHI2QN","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"IVH46KBHI2QNUUA6","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"IVH46KBH","created_at":"2026-07-05T11:14:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IVH46KBHI2QNUUA6JGXQLCFZEU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T13:15:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17b759786343f7692f990afe1c66a6cd69a7174831f36064872915939e323e71","abstract_canon_sha256":"1aaed248e096ccf6486bedddbb36c8f08443737facbaac19b688d22eba072f23"},"schema_version":"1.0"},"canonical_sha256":"454fcf282746a0da501e49af0588b9253cd977a5553f4498bf915d4e2906ff80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:17.169445Z","signature_b64":"D6DnZK74E4ukb0SYFJDCeYZIwZELdKe8fvowb4UbhFDMEwzz8QrXixEZ75UqKodnvrntYJaa6FlwN6HZaOB2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454fcf282746a0da501e49af0588b9253cd977a5553f4498bf915d4e2906ff80","last_reissued_at":"2026-07-05T11:14:17.169028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:17.169028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01639","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":"2026-07-05T11:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ElNmYAH9oI14XbwuENWDiRsrkzcnyc1bVny6TkNBWINg1sELzAfvu+yq13lmPv8krAO5eFI5D6IcsWjFhchbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:34:06.101448Z"},"content_sha256":"78d22ac99a94966584440d13dd40c99fd18069a1845f526094564bb6df2b155e","schema_version":"1.0","event_id":"sha256:78d22ac99a94966584440d13dd40c99fd18069a1845f526094564bb6df2b155e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IVH46KBHI2QNUUA6JGXQLCFZEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changxu Wei, Huaze Tang, Wenbo Ding, Yixian Zhang","submitted_at":"2025-06-02T13:15:30Z","abstract_excerpt":"The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) divergence for policy updates. However, this approach leads to an intractable optimal projection policy, necessitating gradient-based approximations that can suffer from instability and poor sample efficiency. This paper investigates the alternative use of forward KL divergence within SAC. We demonstrate that for Gaussian policies, forward KL divergence yields an explicit optimal projection policy -- corresponding to the me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01639","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/2506.01639/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":"2026-07-05T11:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFm8n/azQSoO7z0s3SxlHYUrwUkyw9bFta/PLFljc7jI2wOhTWeF7T4eKr25lbcktiYbNXQNQC6bnQttk6llBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:34:06.102424Z"},"content_sha256":"882bd05ef78c1bf56f016aeef702ac9fe7be9dc08ac9193191250781efe6b992","schema_version":"1.0","event_id":"sha256:882bd05ef78c1bf56f016aeef702ac9fe7be9dc08ac9193191250781efe6b992"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/bundle.json","state_url":"https://pith.science/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/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":"2026-08-09T09:34:06Z","links":{"resolver":"https://pith.science/pith/IVH46KBHI2QNUUA6JGXQLCFZEU","bundle":"https://pith.science/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/bundle.json","state":"https://pith.science/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVH46KBHI2QNUUA6JGXQLCFZEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVH46KBHI2QNUUA6JGXQLCFZEU","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":"1aaed248e096ccf6486bedddbb36c8f08443737facbaac19b688d22eba072f23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T13:15:30Z","title_canon_sha256":"17b759786343f7692f990afe1c66a6cd69a7174831f36064872915939e323e71"},"schema_version":"1.0","source":{"id":"2506.01639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01639","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01639v1","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01639","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"IVH46KBHI2QN","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"IVH46KBHI2QNUUA6","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"IVH46KBH","created_at":"2026-07-05T11:14:17Z"}],"graph_snapshots":[{"event_id":"sha256:882bd05ef78c1bf56f016aeef702ac9fe7be9dc08ac9193191250781efe6b992","target":"graph","created_at":"2026-07-05T11:14:17Z","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/2506.01639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) divergence for policy updates. However, this approach leads to an intractable optimal projection policy, necessitating gradient-based approximations that can suffer from instability and poor sample efficiency. This paper investigates the alternative use of forward KL divergence within SAC. We demonstrate that for Gaussian policies, forward KL divergence yields an explicit optimal projection policy -- corresponding to the me","authors_text":"Changxu Wei, Huaze Tang, Wenbo Ding, Yixian Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T13:15:30Z","title":"Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01639","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":"sha256:78d22ac99a94966584440d13dd40c99fd18069a1845f526094564bb6df2b155e","target":"record","created_at":"2026-07-05T11:14:17Z","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":"1aaed248e096ccf6486bedddbb36c8f08443737facbaac19b688d22eba072f23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T13:15:30Z","title_canon_sha256":"17b759786343f7692f990afe1c66a6cd69a7174831f36064872915939e323e71"},"schema_version":"1.0","source":{"id":"2506.01639","kind":"arxiv","version":1}},"canonical_sha256":"454fcf282746a0da501e49af0588b9253cd977a5553f4498bf915d4e2906ff80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"454fcf282746a0da501e49af0588b9253cd977a5553f4498bf915d4e2906ff80","first_computed_at":"2026-07-05T11:14:17.169028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:17.169028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D6DnZK74E4ukb0SYFJDCeYZIwZELdKe8fvowb4UbhFDMEwzz8QrXixEZ75UqKodnvrntYJaa6FlwN6HZaOB2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:17.169445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d22ac99a94966584440d13dd40c99fd18069a1845f526094564bb6df2b155e","sha256:882bd05ef78c1bf56f016aeef702ac9fe7be9dc08ac9193191250781efe6b992"],"state_sha256":"dfee7ac38791becc7150b905a5ead38fda2bab1918effa512e3ce15db92d1af4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MIevFMlT6bjwIpbesa5zAhFaDA9pnlcLxxI4gadeleEdSy1CPoPfd9qudk27k8XXN9kd2F2TGWL6uBhwWrETBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:34:06.127610Z","bundle_sha256":"4a07858e477b4b8a355fa4fa5e1c9e7f4518a0ec25b0a27ad59a84a3b00f6fcd"}}