{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TTVQDMV4AE4LXHPQSBTL7AX4PA","short_pith_number":"pith:TTVQDMV4","canonical_record":{"source":{"id":"2002.03327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-09T09:50:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"849dea1ee05258fbf1fad2db57be3a36c9490a821e0a5bfbd1f070e3c23a6f6c","abstract_canon_sha256":"83f0bce775b8bd3263cc0e9a5c93963cb41f659dd22d91ed3f93c0d138525069"},"schema_version":"1.0"},"canonical_sha256":"9ceb01b2bc0138bb9df09066bf82fc780ceb7e1f36d6f3dee777c0e647005814","source":{"kind":"arxiv","id":"2002.03327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03327","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03327v2","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03327","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"TTVQDMV4AE4L","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"TTVQDMV4AE4LXHPQ","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"TTVQDMV4","created_at":"2026-07-05T01:12:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TTVQDMV4AE4LXHPQSBTL7AX4PA","target":"record","payload":{"canonical_record":{"source":{"id":"2002.03327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-09T09:50:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"849dea1ee05258fbf1fad2db57be3a36c9490a821e0a5bfbd1f070e3c23a6f6c","abstract_canon_sha256":"83f0bce775b8bd3263cc0e9a5c93963cb41f659dd22d91ed3f93c0d138525069"},"schema_version":"1.0"},"canonical_sha256":"9ceb01b2bc0138bb9df09066bf82fc780ceb7e1f36d6f3dee777c0e647005814","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:36.973478Z","signature_b64":"B71ViT3DonvH0Au/vZf/4AsUQpQmBO4k8jbLDD76BzW3Ot8oOxayuezbC5v6EcLwVTUNN7Si/E5vHhmoaEjGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ceb01b2bc0138bb9df09066bf82fc780ceb7e1f36d6f3dee777c0e647005814","last_reissued_at":"2026-07-05T01:12:36.973022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:36.973022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.03327","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":"2026-07-05T01:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"em8WXu8URhFSW/W5NoXkkbL3PpGztj3zcZzHGXD7DsMi/ouQpaDzN8xPM+L1kph0bOsQDWDDjnj5eo82Ni6cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:45:58.546253Z"},"content_sha256":"e5ccba78a28bc215c0268172e9969cf61539858dd8128e50b1a76bbba8c609b6","schema_version":"1.0","event_id":"sha256:e5ccba78a28bc215c0268172e9969cf61539858dd8128e50b1a76bbba8c609b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TTVQDMV4AE4LXHPQSBTL7AX4PA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Tessler, Shie Mannor","submitted_at":"2020-02-09T09:50:07Z","abstract_excerpt":"In reinforcement learning, the discount factor $\\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become unstable when the effective planning horizon is long, recent works refer to $\\gamma$ as a hyper-parameter -- thus changing the underlying MDP and potentially leading the agent towards sub-optimal behavior on the original task. In this work, we introduce \\emph{reward tweaking}. Reward tweaking learns a surrogate reward function $\\tilde r$ for the discounted setting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03327","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/2002.03327/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":"2026-07-05T01:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4ufhoJ1Zumoy5LoHAdzKE+CrBEO9SBPqIAXuiMBKzZefdT3IqECOFLim3j0PCHNuBcw5ijB0A65bW2Z4YA2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:45:58.546953Z"},"content_sha256":"59c8a41beaee1e4a5d23e023cb6b180903e9a52dd78627d18fbbfd75e054240f","schema_version":"1.0","event_id":"sha256:59c8a41beaee1e4a5d23e023cb6b180903e9a52dd78627d18fbbfd75e054240f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/bundle.json","state_url":"https://pith.science/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/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":"2026-08-16T11:45:58Z","links":{"resolver":"https://pith.science/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA","bundle":"https://pith.science/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/bundle.json","state":"https://pith.science/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTVQDMV4AE4LXHPQSBTL7AX4PA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TTVQDMV4AE4LXHPQSBTL7AX4PA","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":"83f0bce775b8bd3263cc0e9a5c93963cb41f659dd22d91ed3f93c0d138525069","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-09T09:50:07Z","title_canon_sha256":"849dea1ee05258fbf1fad2db57be3a36c9490a821e0a5bfbd1f070e3c23a6f6c"},"schema_version":"1.0","source":{"id":"2002.03327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03327","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03327v2","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03327","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"TTVQDMV4AE4L","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"TTVQDMV4AE4LXHPQ","created_at":"2026-07-05T01:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"TTVQDMV4","created_at":"2026-07-05T01:12:36Z"}],"graph_snapshots":[{"event_id":"sha256:59c8a41beaee1e4a5d23e023cb6b180903e9a52dd78627d18fbbfd75e054240f","target":"graph","created_at":"2026-07-05T01:12:36Z","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/2002.03327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, the discount factor $\\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become unstable when the effective planning horizon is long, recent works refer to $\\gamma$ as a hyper-parameter -- thus changing the underlying MDP and potentially leading the agent towards sub-optimal behavior on the original task. In this work, we introduce \\emph{reward tweaking}. Reward tweaking learns a surrogate reward function $\\tilde r$ for the discounted setting ","authors_text":"Chen Tessler, Shie Mannor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-09T09:50:07Z","title":"Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03327","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:e5ccba78a28bc215c0268172e9969cf61539858dd8128e50b1a76bbba8c609b6","target":"record","created_at":"2026-07-05T01:12:36Z","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":"83f0bce775b8bd3263cc0e9a5c93963cb41f659dd22d91ed3f93c0d138525069","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-09T09:50:07Z","title_canon_sha256":"849dea1ee05258fbf1fad2db57be3a36c9490a821e0a5bfbd1f070e3c23a6f6c"},"schema_version":"1.0","source":{"id":"2002.03327","kind":"arxiv","version":2}},"canonical_sha256":"9ceb01b2bc0138bb9df09066bf82fc780ceb7e1f36d6f3dee777c0e647005814","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ceb01b2bc0138bb9df09066bf82fc780ceb7e1f36d6f3dee777c0e647005814","first_computed_at":"2026-07-05T01:12:36.973022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:12:36.973022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B71ViT3DonvH0Au/vZf/4AsUQpQmBO4k8jbLDD76BzW3Ot8oOxayuezbC5v6EcLwVTUNN7Si/E5vHhmoaEjGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:12:36.973478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5ccba78a28bc215c0268172e9969cf61539858dd8128e50b1a76bbba8c609b6","sha256:59c8a41beaee1e4a5d23e023cb6b180903e9a52dd78627d18fbbfd75e054240f"],"state_sha256":"ccbf66326d1ac7a14c9b3b7363313b45a07fe6afc56a2477dd33caac64482e4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wyTikl/pkHiH4TfirPmR+PBztrnMQ4xtYbCyrMK9O9IHf8MGyIxR2HqZoIklY0Gct3fPzhXn6tSfId1XPINqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T11:45:58.554978Z","bundle_sha256":"5a08a79ff93933026e7654f1019581ce75dde47a8396505f3c9ffd9c2a18891e"}}