{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A4UYMXXIALBRYBGEX2ZWWCIG5Q","short_pith_number":"pith:A4UYMXXI","canonical_record":{"source":{"id":"2212.07536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T22:43:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be6b3e87e38255c7c9c59e261497a68349a9a186f7e17e9a991111b8e7b801bd","abstract_canon_sha256":"23d19eabda51bc25c09893121764f169c7c4fec0a7023d9d1456cee2f5e024c9"},"schema_version":"1.0"},"canonical_sha256":"0729865ee802c31c04c4beb36b0906ec027fb03f7afe9c7d08344f831303667b","source":{"kind":"arxiv","id":"2212.07536","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07536","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07536v1","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07536","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"A4UYMXXIALBR","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"A4UYMXXIALBRYBGE","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"A4UYMXXI","created_at":"2026-07-05T05:25:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A4UYMXXIALBRYBGEX2ZWWCIG5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2212.07536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T22:43:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be6b3e87e38255c7c9c59e261497a68349a9a186f7e17e9a991111b8e7b801bd","abstract_canon_sha256":"23d19eabda51bc25c09893121764f169c7c4fec0a7023d9d1456cee2f5e024c9"},"schema_version":"1.0"},"canonical_sha256":"0729865ee802c31c04c4beb36b0906ec027fb03f7afe9c7d08344f831303667b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:33.953301Z","signature_b64":"2gejJQcGxearnWn3Ap0MjTsxjOjA9KT8I4qa2eCuGvEThy7Lp3ZyDLYmkhPiNkMqlGLQtX5lWZslKkrWoJ0XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0729865ee802c31c04c4beb36b0906ec027fb03f7afe9c7d08344f831303667b","last_reissued_at":"2026-07-05T05:25:33.952838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:33.952838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.07536","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":"2026-07-05T05:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7eP/1XOvvKNcguN51cBUxzZQbbpGCHF9lfnove1WRwXAqIRMZ8WcwFkqg+xgazrdUWwaB5Sa+x99LfLQimpEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:14:35.955623Z"},"content_sha256":"8b4ee873f0862a440213527a6e3dd3f27efc547ab3e1b4e954e24250966478ef","schema_version":"1.0","event_id":"sha256:8b4ee873f0862a440213527a6e3dd3f27efc547ab3e1b4e954e24250966478ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A4UYMXXIALBRYBGEX2ZWWCIG5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Policy Optimization in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Md Masudur Rahman, Yexiang Xue","submitted_at":"2022-12-14T22:43:56Z","abstract_excerpt":"The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of exploration, resulting from the variance of the representing distribution. Entropy can play an essential role in policy optimization by selecting the stochastic policy, which eventually helps better explore the environment in reinforcement learning (RL). However, the stochasticity often reduces as the training progresses; thus, the policy becomes less explor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07536","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/2212.07536/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":"2026-07-05T05:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sQ1HATFIFKokbSUE4YeHDLlUXe78qfMrElw6EZpGGx4FDz5g8p/q97PYlDYZ8bFpECE+/fKjutjZGXwyIHzKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:14:35.956147Z"},"content_sha256":"18f88d2628072d48113d637fa4d61326f6ab56220ba2639275e001efcfe4fe73","schema_version":"1.0","event_id":"sha256:18f88d2628072d48113d637fa4d61326f6ab56220ba2639275e001efcfe4fe73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/bundle.json","state_url":"https://pith.science/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/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":"2026-08-10T05:14:35Z","links":{"resolver":"https://pith.science/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q","bundle":"https://pith.science/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/bundle.json","state":"https://pith.science/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4UYMXXIALBRYBGEX2ZWWCIG5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A4UYMXXIALBRYBGEX2ZWWCIG5Q","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":"23d19eabda51bc25c09893121764f169c7c4fec0a7023d9d1456cee2f5e024c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T22:43:56Z","title_canon_sha256":"be6b3e87e38255c7c9c59e261497a68349a9a186f7e17e9a991111b8e7b801bd"},"schema_version":"1.0","source":{"id":"2212.07536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07536","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07536v1","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07536","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"A4UYMXXIALBR","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"A4UYMXXIALBRYBGE","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"A4UYMXXI","created_at":"2026-07-05T05:25:33Z"}],"graph_snapshots":[{"event_id":"sha256:18f88d2628072d48113d637fa4d61326f6ab56220ba2639275e001efcfe4fe73","target":"graph","created_at":"2026-07-05T05:25:33Z","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/2212.07536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of exploration, resulting from the variance of the representing distribution. Entropy can play an essential role in policy optimization by selecting the stochastic policy, which eventually helps better explore the environment in reinforcement learning (RL). However, the stochasticity often reduces as the training progresses; thus, the policy becomes less explor","authors_text":"Md Masudur Rahman, Yexiang Xue","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T22:43:56Z","title":"Robust Policy Optimization in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07536","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":"sha256:8b4ee873f0862a440213527a6e3dd3f27efc547ab3e1b4e954e24250966478ef","target":"record","created_at":"2026-07-05T05:25:33Z","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":"23d19eabda51bc25c09893121764f169c7c4fec0a7023d9d1456cee2f5e024c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T22:43:56Z","title_canon_sha256":"be6b3e87e38255c7c9c59e261497a68349a9a186f7e17e9a991111b8e7b801bd"},"schema_version":"1.0","source":{"id":"2212.07536","kind":"arxiv","version":1}},"canonical_sha256":"0729865ee802c31c04c4beb36b0906ec027fb03f7afe9c7d08344f831303667b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0729865ee802c31c04c4beb36b0906ec027fb03f7afe9c7d08344f831303667b","first_computed_at":"2026-07-05T05:25:33.952838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:33.952838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2gejJQcGxearnWn3Ap0MjTsxjOjA9KT8I4qa2eCuGvEThy7Lp3ZyDLYmkhPiNkMqlGLQtX5lWZslKkrWoJ0XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:33.953301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.07536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b4ee873f0862a440213527a6e3dd3f27efc547ab3e1b4e954e24250966478ef","sha256:18f88d2628072d48113d637fa4d61326f6ab56220ba2639275e001efcfe4fe73"],"state_sha256":"d51ec3b3b4ae410546555e0a20f975765c4c0d598733ba6a8358416a93a2f265"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNTH0x4d8OSfYJtodw2O+53ZOc502WNQ/gMA/074v3yOHjV5OAHHXz8V36CwmsZ3QxOySwNqBtxmiCDjXjsADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:14:35.961311Z","bundle_sha256":"04a4b1e414b9a74b1a80531190e44de019914f0f34ee0bea627df4217a29df64"}}