{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MFWDDLGER7SWU4DUYIJK7WWAYD","short_pith_number":"pith:MFWDDLGE","canonical_record":{"source":{"id":"1907.10247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T05:46:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3a64e9a0ddbb4f4427c9db35a328e19cee0146e246d6178eb17399328475657b","abstract_canon_sha256":"81dfeaaf11a92cab2d964f87686da5c9a955754405f7a3a883272ae120bf4fea"},"schema_version":"1.0"},"canonical_sha256":"616c31acc48fe56a7074c212afdac0c0e74b24e3bff0d957fc5a40f871d9833c","source":{"kind":"arxiv","id":"1907.10247","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10247","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10247v3","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10247","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"MFWDDLGER7SW","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"MFWDDLGER7SWU4DU","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"MFWDDLGE","created_at":"2026-07-05T02:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MFWDDLGER7SWU4DUYIJK7WWAYD","target":"record","payload":{"canonical_record":{"source":{"id":"1907.10247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T05:46:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3a64e9a0ddbb4f4427c9db35a328e19cee0146e246d6178eb17399328475657b","abstract_canon_sha256":"81dfeaaf11a92cab2d964f87686da5c9a955754405f7a3a883272ae120bf4fea"},"schema_version":"1.0"},"canonical_sha256":"616c31acc48fe56a7074c212afdac0c0e74b24e3bff0d957fc5a40f871d9833c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:08.864646Z","signature_b64":"xiohI+XJ82oOrrXlI/rmH36HBku6KJYkH+msHWM3VPyVqbQYXeglVEZRsMeaUuMzCeoVV+PaLCquvIvr+BUJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"616c31acc48fe56a7074c212afdac0c0e74b24e3bff0d957fc5a40f871d9833c","last_reissued_at":"2026-07-05T02:15:08.864060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:08.864060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.10247","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pft+lHYD0DfjsCPvtIr8OtNN4ZJVe7yKZP46SstWlOs6x9ucHgURy69Bx9sJrSOmYzcZZCgdIev8pNYXyOqKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T11:34:58.719044Z"},"content_sha256":"5f39d2da712c5b678b970bfe37bb7cf139bc1cd4d1b73abd9d9e005bbb3bdfb8","schema_version":"1.0","event_id":"sha256:5f39d2da712c5b678b970bfe37bb7cf139bc1cd4d1b73abd9d9e005bbb3bdfb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MFWDDLGER7SWU4DUYIJK7WWAYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Jongwook Choi, Marcin Moczulski, Mohammad Norouzi, Samy Bengio, Shengyu Feng, Yijie Guo","submitted_at":"2019-07-24T05:46:27Z","abstract_excerpt":"Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective policies. However, existing methods may overly exploit past successful experiences, which can encourage the agent to adopt sub-optimal and myopic behaviors. In this work, instead of focusing on good experiences with limited diversity, we propose to learn a trajectory-conditioned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10247","kind":"arxiv","version":3},"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/1907.10247/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":"2026-07-05T02:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcHEtL6bELfTURRYDhxKlaM1VKe+0yXqznJUDreaLxqQkbhwTcQf07oHRcVlcIGGARhjQOeu+zm5mzU5EX63CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T11:34:58.719434Z"},"content_sha256":"3a4a576c719c3695289d8a3e9fd5e05735f01cc7cae677ad15dd39c076f6ddab","schema_version":"1.0","event_id":"sha256:3a4a576c719c3695289d8a3e9fd5e05735f01cc7cae677ad15dd39c076f6ddab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/bundle.json","state_url":"https://pith.science/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/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":"2026-07-14T11:34:58Z","links":{"resolver":"https://pith.science/pith/MFWDDLGER7SWU4DUYIJK7WWAYD","bundle":"https://pith.science/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/bundle.json","state":"https://pith.science/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFWDDLGER7SWU4DUYIJK7WWAYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MFWDDLGER7SWU4DUYIJK7WWAYD","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":"81dfeaaf11a92cab2d964f87686da5c9a955754405f7a3a883272ae120bf4fea","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T05:46:27Z","title_canon_sha256":"3a64e9a0ddbb4f4427c9db35a328e19cee0146e246d6178eb17399328475657b"},"schema_version":"1.0","source":{"id":"1907.10247","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10247","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10247v3","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10247","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"MFWDDLGER7SW","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"MFWDDLGER7SWU4DU","created_at":"2026-07-05T02:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"MFWDDLGE","created_at":"2026-07-05T02:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:3a4a576c719c3695289d8a3e9fd5e05735f01cc7cae677ad15dd39c076f6ddab","target":"graph","created_at":"2026-07-05T02:15:08Z","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/1907.10247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective policies. However, existing methods may overly exploit past successful experiences, which can encourage the agent to adopt sub-optimal and myopic behaviors. In this work, instead of focusing on good experiences with limited diversity, we propose to learn a trajectory-conditioned","authors_text":"Honglak Lee, Jongwook Choi, Marcin Moczulski, Mohammad Norouzi, Samy Bengio, Shengyu Feng, Yijie Guo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T05:46:27Z","title":"Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10247","kind":"arxiv","version":3},"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":"sha256:5f39d2da712c5b678b970bfe37bb7cf139bc1cd4d1b73abd9d9e005bbb3bdfb8","target":"record","created_at":"2026-07-05T02:15:08Z","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":"81dfeaaf11a92cab2d964f87686da5c9a955754405f7a3a883272ae120bf4fea","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T05:46:27Z","title_canon_sha256":"3a64e9a0ddbb4f4427c9db35a328e19cee0146e246d6178eb17399328475657b"},"schema_version":"1.0","source":{"id":"1907.10247","kind":"arxiv","version":3}},"canonical_sha256":"616c31acc48fe56a7074c212afdac0c0e74b24e3bff0d957fc5a40f871d9833c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"616c31acc48fe56a7074c212afdac0c0e74b24e3bff0d957fc5a40f871d9833c","first_computed_at":"2026-07-05T02:15:08.864060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:08.864060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xiohI+XJ82oOrrXlI/rmH36HBku6KJYkH+msHWM3VPyVqbQYXeglVEZRsMeaUuMzCeoVV+PaLCquvIvr+BUJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:08.864646Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10247","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f39d2da712c5b678b970bfe37bb7cf139bc1cd4d1b73abd9d9e005bbb3bdfb8","sha256:3a4a576c719c3695289d8a3e9fd5e05735f01cc7cae677ad15dd39c076f6ddab"],"state_sha256":"258c6c62861421ec271f60f2af2e5b2bd6a34d935b49208755baf946fd3bb513"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1WpJgEJ3qdElL1U7i9HiFKKkZ+8Cp5JfbWV/vnFYAAd+Q+CGGTkGZvJgFg/zTNKJWaMnT+1m4NETlMv7NHHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T11:34:58.721695Z","bundle_sha256":"104f7d7ad4ff56f33c42c919954ea6652da972e7599a374ceeb1c35fa3786cd1"}}