{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RERHSAXBRNY4E2MOYO2B5Y2ADT","short_pith_number":"pith:RERHSAXB","canonical_record":{"source":{"id":"2104.04174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T03:13:35Z","cross_cats_sorted":[],"title_canon_sha256":"1a2cd7f7af2ccaddc683c25387277e40a894000559bda8bb811612a4a5a716af","abstract_canon_sha256":"ef171dec43c03cebe6af27a366e633199e166941544eaf3a0b5f16b98935b227"},"schema_version":"1.0"},"canonical_sha256":"89227902e18b71c2698ec3b41ee3401ccc410f475fb6c740e14feeb75d0fb7b4","source":{"kind":"arxiv","id":"2104.04174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04174","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04174v1","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04174","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"RERHSAXBRNY4","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"RERHSAXBRNY4E2MO","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"RERHSAXB","created_at":"2026-07-05T02:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RERHSAXBRNY4E2MOYO2B5Y2ADT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.04174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T03:13:35Z","cross_cats_sorted":[],"title_canon_sha256":"1a2cd7f7af2ccaddc683c25387277e40a894000559bda8bb811612a4a5a716af","abstract_canon_sha256":"ef171dec43c03cebe6af27a366e633199e166941544eaf3a0b5f16b98935b227"},"schema_version":"1.0"},"canonical_sha256":"89227902e18b71c2698ec3b41ee3401ccc410f475fb6c740e14feeb75d0fb7b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:36.382216Z","signature_b64":"Dp/272ReH/dNhDkZq5L19e5fv2woxkbAccy4JYhM/6rQ/1DSXhBsd6lYvhmxFynuqWH9lM9scX7wvMN3KQiBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89227902e18b71c2698ec3b41ee3401ccc410f475fb6c740e14feeb75d0fb7b4","last_reissued_at":"2026-07-05T02:30:36.381773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:36.381773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.04174","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":"2026-07-05T02:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGtLplhHW19DEwRMDdB2REMfnteG3J1VjIWc3dyHlRy7UZfPqyshSbUClLXQ/gP39tU4kH10QKwtmorkdEJoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:16:06.542103Z"},"content_sha256":"1174ce34173a687d2a313ac5822cc2bfe9aa415e9f5cc2c472cf8dc210b874ed","schema_version":"1.0","event_id":"sha256:1174ce34173a687d2a313ac5822cc2bfe9aa415e9f5cc2c472cf8dc210b874ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RERHSAXBRNY4E2MOYO2B5Y2ADT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junge Zhang, Kaiqi Huang, Qiyue Yin, Wenzhen Huang","submitted_at":"2021-04-09T03:13:35Z","abstract_excerpt":"Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To alleviate such problem, this paper proposes to adaptively reweight the imaginary transitions, so as to reduce the negative effects of poorly generated trajectories. More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04174","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/2104.04174/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":"2026-07-05T02:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yc+0Mxzm+AcKN7NUZv903LgA1s/KXgzOxwvDOKSHpOAcDi7Cga5sPfUNZ+5Dg7e+SrhvEo2UmGZ1l5pSg9ggAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:16:06.542488Z"},"content_sha256":"2774be0df14b8439f40106aa5c393129148fd155efe8606a82dcb5a655fc5e8d","schema_version":"1.0","event_id":"sha256:2774be0df14b8439f40106aa5c393129148fd155efe8606a82dcb5a655fc5e8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/bundle.json","state_url":"https://pith.science/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/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":"2026-07-10T12:16:06Z","links":{"resolver":"https://pith.science/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT","bundle":"https://pith.science/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/bundle.json","state":"https://pith.science/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RERHSAXBRNY4E2MOYO2B5Y2ADT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RERHSAXBRNY4E2MOYO2B5Y2ADT","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":"ef171dec43c03cebe6af27a366e633199e166941544eaf3a0b5f16b98935b227","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T03:13:35Z","title_canon_sha256":"1a2cd7f7af2ccaddc683c25387277e40a894000559bda8bb811612a4a5a716af"},"schema_version":"1.0","source":{"id":"2104.04174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04174","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04174v1","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04174","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"RERHSAXBRNY4","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"RERHSAXBRNY4E2MO","created_at":"2026-07-05T02:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"RERHSAXB","created_at":"2026-07-05T02:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:2774be0df14b8439f40106aa5c393129148fd155efe8606a82dcb5a655fc5e8d","target":"graph","created_at":"2026-07-05T02:30:36Z","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/2104.04174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To alleviate such problem, this paper proposes to adaptively reweight the imaginary transitions, so as to reduce the negative effects of poorly generated trajectories. More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when ","authors_text":"Junge Zhang, Kaiqi Huang, Qiyue Yin, Wenzhen Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T03:13:35Z","title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04174","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":"sha256:1174ce34173a687d2a313ac5822cc2bfe9aa415e9f5cc2c472cf8dc210b874ed","target":"record","created_at":"2026-07-05T02:30:36Z","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":"ef171dec43c03cebe6af27a366e633199e166941544eaf3a0b5f16b98935b227","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T03:13:35Z","title_canon_sha256":"1a2cd7f7af2ccaddc683c25387277e40a894000559bda8bb811612a4a5a716af"},"schema_version":"1.0","source":{"id":"2104.04174","kind":"arxiv","version":1}},"canonical_sha256":"89227902e18b71c2698ec3b41ee3401ccc410f475fb6c740e14feeb75d0fb7b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89227902e18b71c2698ec3b41ee3401ccc410f475fb6c740e14feeb75d0fb7b4","first_computed_at":"2026-07-05T02:30:36.381773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:36.381773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dp/272ReH/dNhDkZq5L19e5fv2woxkbAccy4JYhM/6rQ/1DSXhBsd6lYvhmxFynuqWH9lM9scX7wvMN3KQiBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:36.382216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1174ce34173a687d2a313ac5822cc2bfe9aa415e9f5cc2c472cf8dc210b874ed","sha256:2774be0df14b8439f40106aa5c393129148fd155efe8606a82dcb5a655fc5e8d"],"state_sha256":"0db0f4e22465d0b2536aa95f6e5ae24770e4b321739904bee8979f394b9d82a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"93sTvi7vAvcNSrUYfx+D2r0lHVK2wLJ/4GhBch1pgViMRwxA+Gh+veH8qeBkX+JlPJxK13BlffKDvlKVvv6SDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:16:06.544432Z","bundle_sha256":"1203f4ad70f3baec733b2feda4b43103d5a2089eed1ac8a15ae7be8dad0dc237"}}