{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QTFKONS7YRBUCIRNHTMZHKSGZI","short_pith_number":"pith:QTFKONS7","canonical_record":{"source":{"id":"2002.12089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-27T13:43:51Z","cross_cats_sorted":[],"title_canon_sha256":"e1376413957f2bed0e3ccb5eec7a1363dc81e46aa5ecfa4c06fb77b124e2b420","abstract_canon_sha256":"6ea5ce466f8ce9f08d1817e1a296cc38daac4e9c2a7b2985751b32d43950a0c2"},"schema_version":"1.0"},"canonical_sha256":"84caa7365fc44341222d3cd993aa46ca04b9a67f617090bf4bd11a1a249a5cf7","source":{"kind":"arxiv","id":"2002.12089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12089","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12089v1","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12089","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"QTFKONS7YRBU","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"QTFKONS7YRBUCIRN","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"QTFKONS7","created_at":"2026-07-05T00:44:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QTFKONS7YRBUCIRNHTMZHKSGZI","target":"record","payload":{"canonical_record":{"source":{"id":"2002.12089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-27T13:43:51Z","cross_cats_sorted":[],"title_canon_sha256":"e1376413957f2bed0e3ccb5eec7a1363dc81e46aa5ecfa4c06fb77b124e2b420","abstract_canon_sha256":"6ea5ce466f8ce9f08d1817e1a296cc38daac4e9c2a7b2985751b32d43950a0c2"},"schema_version":"1.0"},"canonical_sha256":"84caa7365fc44341222d3cd993aa46ca04b9a67f617090bf4bd11a1a249a5cf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:20.335022Z","signature_b64":"eyCnmqtkgL1W+pxw72phjL3KIf4zsMRhLOQ07YNsW1ORowpnTQmJpCOpNQYqNPBsH0dz6v0gG9+aPbT3pYlnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84caa7365fc44341222d3cd993aa46ca04b9a67f617090bf4bd11a1a249a5cf7","last_reissued_at":"2026-07-05T00:44:20.334599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:20.334599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.12089","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":"2026-07-05T00:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zX4qv8cYCsCDEqkmYUCOwmGzyGl1wZ85s7I8LZYuKyhX8WnR6CTdjDXOcWNXgsOepSmGf6EWX8oDHHrpc+uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:41:24.973178Z"},"content_sha256":"f55833800571e9982d28a8f8e7f9f49d8cc9f4377d7645c60207f60d590c2b3f","schema_version":"1.0","event_id":"sha256:f55833800571e9982d28a8f8e7f9f49d8cc9f4377d7645c60207f60d590c2b3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QTFKONS7YRBUCIRNHTMZHKSGZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Binhao Chen, Chengliang Liu, Jian Pu, Junping Zhang, Ke Lin, Liang Gong, Te Sun, Xudong Li, Zhengfeng Zhang","submitted_at":"2020-02-27T13:43:51Z","abstract_excerpt":"Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse rewards. Recently, some reinforcement learning from demonstration (RLfD) methods have shown to be promising in overcoming these problems. However, they usually require considerable demonstrations. In order to tackle these challenges, on the basis of the SAC algorithm we propose a sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discrimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12089","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/2002.12089/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":"2026-07-05T00:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95+n06HCv2iV299PuBF+oF53TVB0aCwbrFkg8Y6c7AwzbUXPcQJ/OIIbTsfJldc40c9ikomvAAqF8qY3D5WzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:41:24.973476Z"},"content_sha256":"0ec84095957158db9c12a455fa2a36272a5318299a3f44cdc788cbb95b799927","schema_version":"1.0","event_id":"sha256:0ec84095957158db9c12a455fa2a36272a5318299a3f44cdc788cbb95b799927"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/bundle.json","state_url":"https://pith.science/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/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":"2026-07-31T19:41:24Z","links":{"resolver":"https://pith.science/pith/QTFKONS7YRBUCIRNHTMZHKSGZI","bundle":"https://pith.science/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/bundle.json","state":"https://pith.science/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTFKONS7YRBUCIRNHTMZHKSGZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QTFKONS7YRBUCIRNHTMZHKSGZI","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":"6ea5ce466f8ce9f08d1817e1a296cc38daac4e9c2a7b2985751b32d43950a0c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-27T13:43:51Z","title_canon_sha256":"e1376413957f2bed0e3ccb5eec7a1363dc81e46aa5ecfa4c06fb77b124e2b420"},"schema_version":"1.0","source":{"id":"2002.12089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12089","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12089v1","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12089","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"QTFKONS7YRBU","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"QTFKONS7YRBUCIRN","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"QTFKONS7","created_at":"2026-07-05T00:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:0ec84095957158db9c12a455fa2a36272a5318299a3f44cdc788cbb95b799927","target":"graph","created_at":"2026-07-05T00:44:20Z","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/2002.12089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse rewards. Recently, some reinforcement learning from demonstration (RLfD) methods have shown to be promising in overcoming these problems. However, they usually require considerable demonstrations. In order to tackle these challenges, on the basis of the SAC algorithm we propose a sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discrimi","authors_text":"Binhao Chen, Chengliang Liu, Jian Pu, Junping Zhang, Ke Lin, Liang Gong, Te Sun, Xudong Li, Zhengfeng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-27T13:43:51Z","title":"Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12089","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:f55833800571e9982d28a8f8e7f9f49d8cc9f4377d7645c60207f60d590c2b3f","target":"record","created_at":"2026-07-05T00:44:20Z","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":"6ea5ce466f8ce9f08d1817e1a296cc38daac4e9c2a7b2985751b32d43950a0c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-27T13:43:51Z","title_canon_sha256":"e1376413957f2bed0e3ccb5eec7a1363dc81e46aa5ecfa4c06fb77b124e2b420"},"schema_version":"1.0","source":{"id":"2002.12089","kind":"arxiv","version":1}},"canonical_sha256":"84caa7365fc44341222d3cd993aa46ca04b9a67f617090bf4bd11a1a249a5cf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84caa7365fc44341222d3cd993aa46ca04b9a67f617090bf4bd11a1a249a5cf7","first_computed_at":"2026-07-05T00:44:20.334599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:20.334599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyCnmqtkgL1W+pxw72phjL3KIf4zsMRhLOQ07YNsW1ORowpnTQmJpCOpNQYqNPBsH0dz6v0gG9+aPbT3pYlnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:20.335022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f55833800571e9982d28a8f8e7f9f49d8cc9f4377d7645c60207f60d590c2b3f","sha256:0ec84095957158db9c12a455fa2a36272a5318299a3f44cdc788cbb95b799927"],"state_sha256":"e246f58f5d9061024afd558f073821c7c734577cdb562e55e4f3d48a29ab4ab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFygpr6hZdBr0w6Nt8NXfeOPT95+D4CgdesyapU4nxnsbobHnJ+9eZ8WwwYSIR2//GfYfGRe361aQARzLDgPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T19:41:24.976642Z","bundle_sha256":"11a648a7685e13ee2c9d5844033a082b3a68b41a94540813d1abfcb647bf5cc7"}}