{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SACCPMS6EZXPWOEAZYXFJHDIDZ","short_pith_number":"pith:SACCPMS6","canonical_record":{"source":{"id":"2305.00286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T15:46:19Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4f5bf2005134cac4f86d913d57417670ea6126819373a9c4522ff765d3a876d3","abstract_canon_sha256":"6fd41003b021176e0a3d3663149abffb027037d58cb67a9e0cae8c4a9b0fabbf"},"schema_version":"1.0"},"canonical_sha256":"900427b25e266efb3880ce2e549c681e4a1e1993533b4afb11057a25d1dc569a","source":{"kind":"arxiv","id":"2305.00286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00286","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00286v1","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00286","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"SACCPMS6EZXP","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"SACCPMS6EZXPWOEA","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"SACCPMS6","created_at":"2026-07-05T06:05:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SACCPMS6EZXPWOEAZYXFJHDIDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T15:46:19Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4f5bf2005134cac4f86d913d57417670ea6126819373a9c4522ff765d3a876d3","abstract_canon_sha256":"6fd41003b021176e0a3d3663149abffb027037d58cb67a9e0cae8c4a9b0fabbf"},"schema_version":"1.0"},"canonical_sha256":"900427b25e266efb3880ce2e549c681e4a1e1993533b4afb11057a25d1dc569a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:39.618454Z","signature_b64":"tKeMLIHjfDFINoLMiEWVJFm5NHCC3VSDtK8TOsdWpXGc0l3xuGQNFBW6MUf4pFh07AmelB2jlhH4GmaGemxUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"900427b25e266efb3880ce2e549c681e4a1e1993533b4afb11057a25d1dc569a","last_reissued_at":"2026-07-05T06:05:39.618037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:39.618037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00286","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":"2026-07-05T06:05:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yAPQjUrAJGSZ7U9/OGujm33+W2AoZFTjXc7dMVKCJSCHEgoJEcCZ5Sz1QG3ZU/kKOsA/N57py5rDQbq7BtgFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:02.017163Z"},"content_sha256":"a341bdcab662d3d00da4ec42c5ab01e5dde7bb47d6c811668a7f0fae80991645","schema_version":"1.0","event_id":"sha256:a341bdcab662d3d00da4ec42c5ab01e5dde7bb47d6c811668a7f0fae80991645"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SACCPMS6EZXPWOEAZYXFJHDIDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alois Knoll, Chenguang Yang, Hang Su, Kai Huang, Mingyang Wang, Shuai Wang, Xiangtong Yao, Zhenshan Bing","submitted_at":"2023-04-29T15:46:19Z","abstract_excerpt":"Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00286","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/2305.00286/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":"2026-07-05T06:05:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"quY0FFp6crAct8Yk13akVHkL56/aOx3DqScWZi+UcQS+JDiB8CTJpdb8OihhD1evw05LcDw2cRd8hpn8faaOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:02.017813Z"},"content_sha256":"bb71062b82601641268f428bfb367b05b060f55dc1c5a59e4120a66518c70dd0","schema_version":"1.0","event_id":"sha256:bb71062b82601641268f428bfb367b05b060f55dc1c5a59e4120a66518c70dd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/bundle.json","state_url":"https://pith.science/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/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":"2026-07-09T06:03:02Z","links":{"resolver":"https://pith.science/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ","bundle":"https://pith.science/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/bundle.json","state":"https://pith.science/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SACCPMS6EZXPWOEAZYXFJHDIDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SACCPMS6EZXPWOEAZYXFJHDIDZ","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":"6fd41003b021176e0a3d3663149abffb027037d58cb67a9e0cae8c4a9b0fabbf","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T15:46:19Z","title_canon_sha256":"4f5bf2005134cac4f86d913d57417670ea6126819373a9c4522ff765d3a876d3"},"schema_version":"1.0","source":{"id":"2305.00286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00286","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00286v1","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00286","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"SACCPMS6EZXP","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"SACCPMS6EZXPWOEA","created_at":"2026-07-05T06:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"SACCPMS6","created_at":"2026-07-05T06:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:bb71062b82601641268f428bfb367b05b060f55dc1c5a59e4120a66518c70dd0","target":"graph","created_at":"2026-07-05T06:05:39Z","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/2305.00286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distribut","authors_text":"Alois Knoll, Chenguang Yang, Hang Su, Kai Huang, Mingyang Wang, Shuai Wang, Xiangtong Yao, Zhenshan Bing","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T15:46:19Z","title":"Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00286","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:a341bdcab662d3d00da4ec42c5ab01e5dde7bb47d6c811668a7f0fae80991645","target":"record","created_at":"2026-07-05T06:05:39Z","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":"6fd41003b021176e0a3d3663149abffb027037d58cb67a9e0cae8c4a9b0fabbf","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T15:46:19Z","title_canon_sha256":"4f5bf2005134cac4f86d913d57417670ea6126819373a9c4522ff765d3a876d3"},"schema_version":"1.0","source":{"id":"2305.00286","kind":"arxiv","version":1}},"canonical_sha256":"900427b25e266efb3880ce2e549c681e4a1e1993533b4afb11057a25d1dc569a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"900427b25e266efb3880ce2e549c681e4a1e1993533b4afb11057a25d1dc569a","first_computed_at":"2026-07-05T06:05:39.618037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:39.618037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKeMLIHjfDFINoLMiEWVJFm5NHCC3VSDtK8TOsdWpXGc0l3xuGQNFBW6MUf4pFh07AmelB2jlhH4GmaGemxUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:39.618454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a341bdcab662d3d00da4ec42c5ab01e5dde7bb47d6c811668a7f0fae80991645","sha256:bb71062b82601641268f428bfb367b05b060f55dc1c5a59e4120a66518c70dd0"],"state_sha256":"79ddef17de456d2a33cb945ffb674f03431095610f3dae6ce174ff6041d10699"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHnFLjPiufnxxquhFi4oqHGO1+jnIXmjk3DujNrmQXiW16uwCmYV0wYgUCpUNy4mb790U/bmX5weE/aVb2huBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:03:02.021081Z","bundle_sha256":"d2ca8286468d64b8209f6b30e5861f88ab7cc6ad02622c1ff8a4891b60cd5422"}}