{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FMBOIBCV3NYT4Y3DKU533QSOIF","short_pith_number":"pith:FMBOIBCV","canonical_record":{"source":{"id":"2101.04178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-11T20:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e4543089bdb74e8adcc0318b9c925c6f5f76974819ce4191d9b2ce960a1dec5","abstract_canon_sha256":"9d027a133d61c777ae5c571c4af1a4ae33eb0a9d2663b11bcd435fafed010046"},"schema_version":"1.0"},"canonical_sha256":"2b02e40455db713e6363553bbdc24e41534fced77a795dd46b9423a7bedd9e84","source":{"kind":"arxiv","id":"2101.04178","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.04178","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"arxiv_version","alias_value":"2101.04178v2","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04178","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_12","alias_value":"FMBOIBCV3NYT","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"FMBOIBCV3NYT4Y3D","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"FMBOIBCV","created_at":"2026-07-05T02:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FMBOIBCV3NYT4Y3DKU533QSOIF","target":"record","payload":{"canonical_record":{"source":{"id":"2101.04178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-11T20:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e4543089bdb74e8adcc0318b9c925c6f5f76974819ce4191d9b2ce960a1dec5","abstract_canon_sha256":"9d027a133d61c777ae5c571c4af1a4ae33eb0a9d2663b11bcd435fafed010046"},"schema_version":"1.0"},"canonical_sha256":"2b02e40455db713e6363553bbdc24e41534fced77a795dd46b9423a7bedd9e84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:07.313825Z","signature_b64":"7wrAYBmzn+YVUGZFYPsrq8rAd/XY6XVQXM3UV9DwI1lcBFBWL0QY7DcSGAOnnd5nH+OyHM+Gz1y8+Xb03Ss4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b02e40455db713e6363553bbdc24e41534fced77a795dd46b9423a7bedd9e84","last_reissued_at":"2026-07-05T02:33:07.313332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:07.313332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.04178","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":"2026-07-05T02:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1N413B5V9hf2NaQkglncbIzxGyO9NPp9qKOiUgdpER68Sotq3U2twTUmCAjYaGEqHOQlBfCWO5gPSY7+z2vAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:32:49.672061Z"},"content_sha256":"4b9f44842e03266983fa6da179b6a2e5fe1330e3b9da27b1b4e3e3174f5c0e23","schema_version":"1.0","event_id":"sha256:4b9f44842e03266983fa6da179b6a2e5fe1330e3b9da27b1b4e3e3174f5c0e23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FMBOIBCV3NYT4Y3DKU533QSOIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Priors for Large Action Spaces in Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dian Wang, Jan-Willem van de Meent, Lawson L. S. Wong, Ondrej Biza, Robert Platt","submitted_at":"2021-01-11T20:30:54Z","abstract_excerpt":"In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide learning. However, acquiring expert demonstrations can be expensive. This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks. The action prior is a probability distribution over actions that summarizes the set of policies found solving prev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04178","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/2101.04178/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":"2026-07-05T02:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwSoS6EKiUjI/p8TDeubl4rQXkOKAcSk+uD88AKeqW7Jjo9oBoGhBNljPRyyPSy1bga/ZNIaxmCpHT8TY3YYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:32:49.672675Z"},"content_sha256":"14c68fdadfd80c0822a590fe9996ba357349e7a5b2aef1fb9c6e6a7dea8412fc","schema_version":"1.0","event_id":"sha256:14c68fdadfd80c0822a590fe9996ba357349e7a5b2aef1fb9c6e6a7dea8412fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/bundle.json","state_url":"https://pith.science/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/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":"2026-08-07T00:32:49Z","links":{"resolver":"https://pith.science/pith/FMBOIBCV3NYT4Y3DKU533QSOIF","bundle":"https://pith.science/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/bundle.json","state":"https://pith.science/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMBOIBCV3NYT4Y3DKU533QSOIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FMBOIBCV3NYT4Y3DKU533QSOIF","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":"9d027a133d61c777ae5c571c4af1a4ae33eb0a9d2663b11bcd435fafed010046","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-11T20:30:54Z","title_canon_sha256":"8e4543089bdb74e8adcc0318b9c925c6f5f76974819ce4191d9b2ce960a1dec5"},"schema_version":"1.0","source":{"id":"2101.04178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.04178","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"arxiv_version","alias_value":"2101.04178v2","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04178","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_12","alias_value":"FMBOIBCV3NYT","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"FMBOIBCV3NYT4Y3D","created_at":"2026-07-05T02:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"FMBOIBCV","created_at":"2026-07-05T02:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:14c68fdadfd80c0822a590fe9996ba357349e7a5b2aef1fb9c6e6a7dea8412fc","target":"graph","created_at":"2026-07-05T02:33:07Z","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/2101.04178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide learning. However, acquiring expert demonstrations can be expensive. This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks. The action prior is a probability distribution over actions that summarizes the set of policies found solving prev","authors_text":"Dian Wang, Jan-Willem van de Meent, Lawson L. S. Wong, Ondrej Biza, Robert Platt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-11T20:30:54Z","title":"Action Priors for Large Action Spaces in Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04178","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":"sha256:4b9f44842e03266983fa6da179b6a2e5fe1330e3b9da27b1b4e3e3174f5c0e23","target":"record","created_at":"2026-07-05T02:33:07Z","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":"9d027a133d61c777ae5c571c4af1a4ae33eb0a9d2663b11bcd435fafed010046","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-11T20:30:54Z","title_canon_sha256":"8e4543089bdb74e8adcc0318b9c925c6f5f76974819ce4191d9b2ce960a1dec5"},"schema_version":"1.0","source":{"id":"2101.04178","kind":"arxiv","version":2}},"canonical_sha256":"2b02e40455db713e6363553bbdc24e41534fced77a795dd46b9423a7bedd9e84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b02e40455db713e6363553bbdc24e41534fced77a795dd46b9423a7bedd9e84","first_computed_at":"2026-07-05T02:33:07.313332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:07.313332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7wrAYBmzn+YVUGZFYPsrq8rAd/XY6XVQXM3UV9DwI1lcBFBWL0QY7DcSGAOnnd5nH+OyHM+Gz1y8+Xb03Ss4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:07.313825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.04178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b9f44842e03266983fa6da179b6a2e5fe1330e3b9da27b1b4e3e3174f5c0e23","sha256:14c68fdadfd80c0822a590fe9996ba357349e7a5b2aef1fb9c6e6a7dea8412fc"],"state_sha256":"c6d49aaadc8c4d6745382d8f5630b42648d0b9cc8055ce963cc13a9990821fa9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgUfIlfcogc/etm5TBjg2nA+XHuYsLIbjc9iZ5Wa/08dnqcW7bHzKimw4qkJ9ET2uU5FAH9+jE9AYmMNtAjzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:32:49.678649Z","bundle_sha256":"c96a79b22606b8b352b2237800846c1ead0691cd0501897e200a64fc1f33902b"}}