{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Z66RKDL2UUQOH2DDAELLUOW6TX","short_pith_number":"pith:Z66RKDL2","canonical_record":{"source":{"id":"1702.06054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-20T16:32:07Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"8216c88565a5ebddf39ec24490361a89a85387ee5648da73f6124c6e9d339bd4","abstract_canon_sha256":"d6a8605ff229315525ba084586d70bd6367b354f911375a714d19f39dc5d0cb2"},"schema_version":"1.0"},"canonical_sha256":"cfbd150d7aa520e3e8630116ba3ade9dd4c7fda9b17e8d528fd13e91ae98fdb6","source":{"kind":"arxiv","id":"1702.06054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06054","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06054v2","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06054","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z66RKDL2UUQO","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_16","alias_value":"Z66RKDL2UUQOH2DD","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_8","alias_value":"Z66RKDL2","created_at":"2026-07-05T01:36:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Z66RKDL2UUQOH2DDAELLUOW6TX","target":"record","payload":{"canonical_record":{"source":{"id":"1702.06054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-20T16:32:07Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"8216c88565a5ebddf39ec24490361a89a85387ee5648da73f6124c6e9d339bd4","abstract_canon_sha256":"d6a8605ff229315525ba084586d70bd6367b354f911375a714d19f39dc5d0cb2"},"schema_version":"1.0"},"canonical_sha256":"cfbd150d7aa520e3e8630116ba3ade9dd4c7fda9b17e8d528fd13e91ae98fdb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:56.383106Z","signature_b64":"hkePRIn+UdPkStgu/seGDlxz1E34LmtqbPUxfci9+3Rru7fAsQ2zLZ0jlSTEHzowtaVVFOMWJb6TqxKGC+RwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfbd150d7aa520e3e8630116ba3ade9dd4c7fda9b17e8d528fd13e91ae98fdb6","last_reissued_at":"2026-07-05T01:36:56.382663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:56.382663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.06054","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":"2026-07-05T01:36:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVN5uo6BagGt9rbo5R3+yF6g9b7SGFhff+TMVuusAWRCNJaExNSVu2tlKhdLdjT2GVxQ25/Vmz1zjPzOpDtWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:19.329285Z"},"content_sha256":"36181dff375f20adc048d3a400c987c533d7d8ecf5ed054ad5fe9f91c0e583f2","schema_version":"1.0","event_id":"sha256:36181dff375f20adc048d3a400c987c533d7d8ecf5ed054ad5fe9f91c0e583f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Z66RKDL2UUQOH2DDAELLUOW6TX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aravind Srinivas, Balaraman Ravindran, Sahil Sharma","submitted_at":"2017-02-20T16:32:07Z","abstract_excerpt":"Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such algorithms make decisions, i.e., select actions to execute, at every single time step of the agent-environment interactions. In this paper, we propose a novel framework, Fine Grained Action Repetition (FiGAR), which enables the agent to decide the action as well as the time scale of repeating it. FiGAR can be used for improving any Deep Reinforcement Learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06054","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/1702.06054/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":"2026-07-05T01:36:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwNdPXXvEZ5e54FuMTdduBFjBO4Kp11xJ/I8lleXzUuXxgyPADx/dCn2i8+G3pHlbz2X2KMy+ndC3VGc0llrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:19.330031Z"},"content_sha256":"b6b3e63d5c244571bb74c19924338cee8366bbf075b5a4e91653e8b16058924c","schema_version":"1.0","event_id":"sha256:b6b3e63d5c244571bb74c19924338cee8366bbf075b5a4e91653e8b16058924c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/bundle.json","state_url":"https://pith.science/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/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":"2026-08-08T16:22:19Z","links":{"resolver":"https://pith.science/pith/Z66RKDL2UUQOH2DDAELLUOW6TX","bundle":"https://pith.science/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/bundle.json","state":"https://pith.science/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z66RKDL2UUQOH2DDAELLUOW6TX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Z66RKDL2UUQOH2DDAELLUOW6TX","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":"d6a8605ff229315525ba084586d70bd6367b354f911375a714d19f39dc5d0cb2","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-20T16:32:07Z","title_canon_sha256":"8216c88565a5ebddf39ec24490361a89a85387ee5648da73f6124c6e9d339bd4"},"schema_version":"1.0","source":{"id":"1702.06054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06054","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06054v2","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06054","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_12","alias_value":"Z66RKDL2UUQO","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_16","alias_value":"Z66RKDL2UUQOH2DD","created_at":"2026-07-05T01:36:56Z"},{"alias_kind":"pith_short_8","alias_value":"Z66RKDL2","created_at":"2026-07-05T01:36:56Z"}],"graph_snapshots":[{"event_id":"sha256:b6b3e63d5c244571bb74c19924338cee8366bbf075b5a4e91653e8b16058924c","target":"graph","created_at":"2026-07-05T01:36:56Z","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/1702.06054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such algorithms make decisions, i.e., select actions to execute, at every single time step of the agent-environment interactions. In this paper, we propose a novel framework, Fine Grained Action Repetition (FiGAR), which enables the agent to decide the action as well as the time scale of repeating it. FiGAR can be used for improving any Deep Reinforcement Learning ","authors_text":"Aravind Srinivas, Balaraman Ravindran, Sahil Sharma","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-20T16:32:07Z","title":"Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06054","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":"sha256:36181dff375f20adc048d3a400c987c533d7d8ecf5ed054ad5fe9f91c0e583f2","target":"record","created_at":"2026-07-05T01:36:56Z","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":"d6a8605ff229315525ba084586d70bd6367b354f911375a714d19f39dc5d0cb2","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-20T16:32:07Z","title_canon_sha256":"8216c88565a5ebddf39ec24490361a89a85387ee5648da73f6124c6e9d339bd4"},"schema_version":"1.0","source":{"id":"1702.06054","kind":"arxiv","version":2}},"canonical_sha256":"cfbd150d7aa520e3e8630116ba3ade9dd4c7fda9b17e8d528fd13e91ae98fdb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfbd150d7aa520e3e8630116ba3ade9dd4c7fda9b17e8d528fd13e91ae98fdb6","first_computed_at":"2026-07-05T01:36:56.382663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:56.382663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hkePRIn+UdPkStgu/seGDlxz1E34LmtqbPUxfci9+3Rru7fAsQ2zLZ0jlSTEHzowtaVVFOMWJb6TqxKGC+RwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:56.383106Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.06054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36181dff375f20adc048d3a400c987c533d7d8ecf5ed054ad5fe9f91c0e583f2","sha256:b6b3e63d5c244571bb74c19924338cee8366bbf075b5a4e91653e8b16058924c"],"state_sha256":"1c995f1a99984609be385761266fee031616db47f30ab813ec8bf77f4dd16281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0q3QBQDz1cPDLEPeR0qiuAvBXf8+NKD6ipcs/Thwq7/JcBzUvQYUzfeLBg0tQsUPophfNNsNdwrNbV1JWJgPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:22:19.336805Z","bundle_sha256":"3910303244c6cc38240f565b03b73e65b448ae9eb9298c647e62c4867a3ae6dc"}}