{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4NDRFIGWIJGZ5KSDCALEADONMT","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":"4bfe6e1b1eef6cfd58fec6f48cc361d54038b0be26e720a75acdfe98e231d4d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T15:30:11Z","title_canon_sha256":"e4ad8cba824c10b43d7606266d79d6e25f67c3113e9510a562eeca400272527d"},"schema_version":"1.0","source":{"id":"2006.04678","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04678","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04678v2","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04678","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"4NDRFIGWIJGZ","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"4NDRFIGWIJGZ5KSD","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"4NDRFIGW","created_at":"2026-07-05T02:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:77e57638d485dd2aa49d528839ac2b4e345e3116d24bf482784e2985be0d9cde","target":"graph","created_at":"2026-07-05T02:23:57Z","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/2006.04678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation Learning (IL) methods seek to match the behavior of an agent with that of an expert. In the present work, we propose a new IL method based on a conceptually simple algorithm: Primal Wasserstein Imitation Learning (PWIL), which ties to the primal form of the Wasserstein distance between the expert and the agent state-action distributions. We present a reward function which is derived offline, as opposed to recent adversarial IL algorithms that learn a reward function through interactions with the environment, and which requires little fine-tuning. We show that we can recover expert be","authors_text":"L\\'eonard Hussenot, Matthieu Geist, Olivier Pietquin, Robert Dadashi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T15:30:11Z","title":"Primal Wasserstein Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04678","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:e2775c6aa281c6a5a71b09c63607709d0f3e2fcfeee1e86d16ea4f2afa02a960","target":"record","created_at":"2026-07-05T02:23:57Z","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":"4bfe6e1b1eef6cfd58fec6f48cc361d54038b0be26e720a75acdfe98e231d4d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T15:30:11Z","title_canon_sha256":"e4ad8cba824c10b43d7606266d79d6e25f67c3113e9510a562eeca400272527d"},"schema_version":"1.0","source":{"id":"2006.04678","kind":"arxiv","version":2}},"canonical_sha256":"e34712a0d6424d9eaa431016400dcd64c2b37b157942c8ae6409a30949e3d0e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e34712a0d6424d9eaa431016400dcd64c2b37b157942c8ae6409a30949e3d0e7","first_computed_at":"2026-07-05T02:23:57.229385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:23:57.229385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQGo33UPKTD8I85BYs9L0MyVue2q4gdZD/hFXFD2ch8RexmIGnRjwQO1d8Q9mt3tpf9WeA8ZOlcqGzoY1GAJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:23:57.229851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.04678","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2775c6aa281c6a5a71b09c63607709d0f3e2fcfeee1e86d16ea4f2afa02a960","sha256:77e57638d485dd2aa49d528839ac2b4e345e3116d24bf482784e2985be0d9cde"],"state_sha256":"ab3c53c1132fa4ceea2a786d5e1604bc1aa65e296f7b24c2c5b1bab3bed041e2"}