{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IJ4FTKJ44MRQGFDP2MC4DKMKAX","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":"d13706194ae2f49e3eda4d8c45bed4198d146768ae39d0727e2a9f56e3fb68a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-27T00:39:19Z","title_canon_sha256":"952b7c1f0242ed77aba937295ec810b02def20799551cee365b986f0a6b2e4cc"},"schema_version":"1.0","source":{"id":"1811.10756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10756","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10756v1","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10756","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"IJ4FTKJ44MRQ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IJ4FTKJ44MRQGFDP","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IJ4FTKJ4","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:605c98e876c556f3be3f47804c6b99501f6728cd9ad00bf32584bd6b548a0407","target":"graph","created_at":"2026-05-17T23:59:47Z","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"},"paper":{"abstract_excerpt":"Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high and low variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. In this paper, we demonstrate the power of the framework in a navigation task, where the robot can dynamical","authors_text":"Andrew Markham, Changhao Chen, Linhai Xie, Niki Trigoni, Phil Blunsom, Sen Wang, Yishu Miao, Zhihua Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-27T00:39:19Z","title":"Learning with Stochastic Guidance for Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10756","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:d6f76193d9181bdb774e0a770b5c06392d6d7f1a0f99698d46217da8c173aea0","target":"record","created_at":"2026-05-17T23:59:47Z","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":"d13706194ae2f49e3eda4d8c45bed4198d146768ae39d0727e2a9f56e3fb68a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-27T00:39:19Z","title_canon_sha256":"952b7c1f0242ed77aba937295ec810b02def20799551cee365b986f0a6b2e4cc"},"schema_version":"1.0","source":{"id":"1811.10756","kind":"arxiv","version":1}},"canonical_sha256":"427859a93ce32303146fd305c1a98a05c38f5ef60117c62099ebbf7defaae347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"427859a93ce32303146fd305c1a98a05c38f5ef60117c62099ebbf7defaae347","first_computed_at":"2026-05-17T23:59:47.624348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:47.624348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7UybmmHo8waxi8Fl0ppltY8pcpw9yo2wBFFeeics/uvjr939ILxw3QRpVvcD/onXJcpku4iqzi4iMl928q/DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:47.624850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6f76193d9181bdb774e0a770b5c06392d6d7f1a0f99698d46217da8c173aea0","sha256:605c98e876c556f3be3f47804c6b99501f6728cd9ad00bf32584bd6b548a0407"],"state_sha256":"ed213fa4a38dfd1d4dc2cc2abadd2581774f294a785c593a91846970f61fc73a"}