{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PLW24I32DJGNVLIN6Q3B4OXNLS","short_pith_number":"pith:PLW24I32","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"},"canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","source":{"kind":"arxiv","id":"2008.06036","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06036","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06036v2","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06036","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"PLW24I32DJGN","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"PLW24I32DJGNVLIN","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"PLW24I32","created_at":"2026-07-05T02:20:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PLW24I32DJGNVLIN6Q3B4OXNLS","target":"record","payload":{"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"},"canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","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"},"source_kind":"arxiv","source_id":"2008.06036","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":"2026-07-05T02:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osb+ak5LMcVuHmdZhZL5w1RdUdrwxLnukh6OTE0NxD+lcCrk3DF3d66WRZQndbzB2L+wKy1InjqsOFf2RYWsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:22:41.171353Z"},"content_sha256":"d5e517faa127b2c13e5678b0fe81c0de1b1bfb6e31cd35597e0b14397bf9a9cb","schema_version":"1.0","event_id":"sha256:d5e517faa127b2c13e5678b0fe81c0de1b1bfb6e31cd35597e0b14397bf9a9cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PLW24I32DJGNVLIN6Q3B4OXNLS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ypeh/MxUIxO6VLQjYV4cKG8y3TOZuq18cb1bUnzVf0HcF1nfMgsgLtZG2IwVdj5XUVxzaOZgCyMM9qX1HqonCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:22:41.172276Z"},"content_sha256":"01bab570201f23968c5a62cd7d7a0d61e2e14a3c89557d40371b6da50193e58e","schema_version":"1.0","event_id":"sha256:01bab570201f23968c5a62cd7d7a0d61e2e14a3c89557d40371b6da50193e58e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/bundle.json","state_url":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/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":"2026-08-18T01:22:41Z","links":{"resolver":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS","bundle":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/bundle.json","state":"https://pith.science/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLW24I32DJGNVLIN6Q3B4OXNLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PLW24I32DJGNVLIN6Q3B4OXNLS","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":"77f39e9bfbcb1d3d5d90f6f3626b6b65a6f4cc440e6ad2cea20e3aa9152b0759","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-13T17:49:18Z","title_canon_sha256":"bfa161bfac461dd72443a03fdaae9869f509282e3a9347fcdbedbc66b9cf5e6d"},"schema_version":"1.0","source":{"id":"2008.06036","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06036","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06036v2","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06036","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"PLW24I32DJGN","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"PLW24I32DJGNVLIN","created_at":"2026-07-05T02:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"PLW24I32","created_at":"2026-07-05T02:20:29Z"}],"graph_snapshots":[{"event_id":"sha256:01bab570201f23968c5a62cd7d7a0d61e2e14a3c89557d40371b6da50193e58e","target":"graph","created_at":"2026-07-05T02:20:29Z","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/2008.06036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Nadav Merlis, Shie Mannor, Yonathan Efroni","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-13T17:49:18Z","title":"Reinforcement Learning with Trajectory Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06036","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:d5e517faa127b2c13e5678b0fe81c0de1b1bfb6e31cd35597e0b14397bf9a9cb","target":"record","created_at":"2026-07-05T02:20:29Z","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":"77f39e9bfbcb1d3d5d90f6f3626b6b65a6f4cc440e6ad2cea20e3aa9152b0759","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-13T17:49:18Z","title_canon_sha256":"bfa161bfac461dd72443a03fdaae9869f509282e3a9347fcdbedbc66b9cf5e6d"},"schema_version":"1.0","source":{"id":"2008.06036","kind":"arxiv","version":2}},"canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7aedae237a1a4cdaad0df4361e3aed5cb4a8e99b0a9c87fa3d06c883610da28e","first_computed_at":"2026-07-05T02:20:29.333366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:29.333366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nLkKGdCPnT1Z1tPu6DFLUFn+SFM0rg66m+eWrk2oZwLFuTIA/q1xtGOFKjdpeexUvUlkLGqrPAXlTMlSAIziDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:29.333779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.06036","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e517faa127b2c13e5678b0fe81c0de1b1bfb6e31cd35597e0b14397bf9a9cb","sha256:01bab570201f23968c5a62cd7d7a0d61e2e14a3c89557d40371b6da50193e58e"],"state_sha256":"04d56bd9a9dbfffd83b9056806f839d0e88f533c65dafbbde4cd51f6fb0d45b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVMETmzPD6QO5Il/f4YHrlpcRzmdF9XGgq9McUVqPgWhHyaKfZhHUKQHBwc7f5XPtbj7BAC8lcAEDKXWZ7EdBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:22:41.184446Z","bundle_sha256":"d83db9278307effc61321e72eb2bc9fd901dc16db8cb18257afefd76ad9c15b1"}}