{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PLW24I32DJGNVLIN6Q3B4OXNLS","short_pith_number":"pith:PLW24I32","schema_version":"1.0","canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","source":{"kind":"arxiv","id":"2008.06036","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Trajectory Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Merlis, Shie Mannor, Yonathan Efroni","submitted_at":"2020-08-13T17:49:18Z","abstract_excerpt":"The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first step towards relaxing this assumption and require a weaker form of feedback, which we refer to as \\emph{trajectory feedback}. Instead of observing the reward obtained after every action, we assume we only receive a score that represents the quality of the whole trajectory observed by the agent, namely, the sum of all rewards obtained over this trajectory. We "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.06036","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-13T17:49:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bfa161bfac461dd72443a03fdaae9869f509282e3a9347fcdbedbc66b9cf5e6d","abstract_canon_sha256":"77f39e9bfbcb1d3d5d90f6f3626b6b65a6f4cc440e6ad2cea20e3aa9152b0759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:29.333779Z","signature_b64":"nLkKGdCPnT1Z1tPu6DFLUFn+SFM0rg66m+eWrk2oZwLFuTIA/q1xtGOFKjdpeexUvUlkLGqrPAXlTMlSAIziDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","last_reissued_at":"2026-07-05T02:20:29.333366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:29.333366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Trajectory Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Merlis, Shie Mannor, Yonathan Efroni","submitted_at":"2020-08-13T17:49:18Z","abstract_excerpt":"The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first step towards relaxing this assumption and require a weaker form of feedback, which we refer to as \\emph{trajectory feedback}. Instead of observing the reward obtained after every action, we assume we only receive a score that represents the quality of the whole trajectory observed by the agent, namely, the sum of all rewards obtained over this trajectory. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06036","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/2008.06036/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.06036","created_at":"2026-07-05T02:20:29.333432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06036v2","created_at":"2026-07-05T02:20:29.333432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06036","created_at":"2026-07-05T02:20:29.333432+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLW24I32DJGN","created_at":"2026-07-05T02:20:29.333432+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLW24I32DJGNVLIN","created_at":"2026-07-05T02:20:29.333432+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLW24I32","created_at":"2026-07-05T02:20:29.333432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10386","citing_title":"Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS","json":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS.json","graph_json":"https://pith.science/api/pith-number/PLW24I32DJGNVLIN6Q3B4OXNLS/graph.json","events_json":"https://pith.science/api/pith-number/PLW24I32DJGNVLIN6Q3B4OXNLS/events.json","paper":"https://pith.science/paper/PLW24I32"},"agent_actions":{"view_html":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS","download_json":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS.json","view_paper":"https://pith.science/paper/PLW24I32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06036&json=true","fetch_graph":"https://pith.science/api/pith-number/PLW24I32DJGNVLIN6Q3B4OXNLS/graph.json","fetch_events":"https://pith.science/api/pith-number/PLW24I32DJGNVLIN6Q3B4OXNLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/action/storage_attestation","attest_author":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/action/author_attestation","sign_citation":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/action/citation_signature","submit_replication":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/action/replication_record"}},"created_at":"2026-07-05T02:20:29.333432+00:00","updated_at":"2026-07-05T02:20:29.333432+00:00"}