{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:R4QXBDZOQI2RUPZLRDE4OSDDEL","short_pith_number":"pith:R4QXBDZO","canonical_record":{"source":{"id":"1809.08337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-09-21T23:02:42Z","cross_cats_sorted":[],"title_canon_sha256":"0e52cecbfbd50dcd46c2fc56cf30ced96750462d5dfb273e616f2143d9d5a79b","abstract_canon_sha256":"202656699e4c4384ae7088049bbf5b84b341641e967c7f0e005846055def2524"},"schema_version":"1.0"},"canonical_sha256":"8f21708f2e82351a3f2b88c9c7486322d69783e5955418401b79956aea4c34d3","source":{"kind":"arxiv","id":"1809.08337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08337","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08337v1","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08337","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"R4QXBDZOQI2R","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R4QXBDZOQI2RUPZL","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R4QXBDZO","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:R4QXBDZOQI2RUPZLRDE4OSDDEL","target":"record","payload":{"canonical_record":{"source":{"id":"1809.08337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-09-21T23:02:42Z","cross_cats_sorted":[],"title_canon_sha256":"0e52cecbfbd50dcd46c2fc56cf30ced96750462d5dfb273e616f2143d9d5a79b","abstract_canon_sha256":"202656699e4c4384ae7088049bbf5b84b341641e967c7f0e005846055def2524"},"schema_version":"1.0"},"canonical_sha256":"8f21708f2e82351a3f2b88c9c7486322d69783e5955418401b79956aea4c34d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:08.770383Z","signature_b64":"CCt/gvomX334eUjjw+c+ugZ2nd11Ts3NekxeOMobGt6bA0GwHb+dqOqWPQtPpOpIwXzFgRtVLu4FUeBkIqZsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f21708f2e82351a3f2b88c9c7486322d69783e5955418401b79956aea4c34d3","last_reissued_at":"2026-05-18T00:05:08.769801Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:08.769801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.08337","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":"2026-05-18T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g46IfCJcLc+d75e7C6hk5/gwo3Gfxt/f2rubfu3RQhLt73CJ79Y1xzwc++D6tLhQOz1UFX1/12RQZfVotMwqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:00:15.235046Z"},"content_sha256":"74c1a5bbc18ac97e7c869d687ae5755c7a0a848ad95b11a8e345d357e8526a93","schema_version":"1.0","event_id":"sha256:74c1a5bbc18ac97e7c869d687ae5755c7a0a848ad95b11a8e345d357e8526a93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:R4QXBDZOQI2RUPZLRDE4OSDDEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hung Manh La, Mehdi Rahimi, Spencer Gibb, Yantao Shen","submitted_at":"2018-09-21T23:02:42Z","abstract_excerpt":"In this paper, a comparison of reinforcement learning algorithms and their performance on a robot box pushing task is provided. The robot box pushing problem is structured as both a single-agent problem and also a multi-agent problem. A Q-learning algorithm is applied to the single-agent box pushing problem, and three different Q-learning algorithms are applied to the multi-agent box pushing problem. Both sets of algorithms are applied on a dynamic environment that is comprised of static objects, a static goal location, a dynamic box location, and dynamic agent positions. A simulation environm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08337","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":""},"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":"2026-05-18T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CIdMKXxolbkQD9wSoXQY2x8PjsVQXQOOf5BiOiFNIjzPpwPIBXZ/bn8x9WG3Ul/dDuzYfkKz1QrmPYBnfbLsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:00:15.235424Z"},"content_sha256":"43e82278325b9c9768a5f9119c35bf424058b852114c338657d038e879c8c2b0","schema_version":"1.0","event_id":"sha256:43e82278325b9c9768a5f9119c35bf424058b852114c338657d038e879c8c2b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/bundle.json","state_url":"https://pith.science/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/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":"2026-06-04T17:00:15Z","links":{"resolver":"https://pith.science/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL","bundle":"https://pith.science/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/bundle.json","state":"https://pith.science/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4QXBDZOQI2RUPZLRDE4OSDDEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:R4QXBDZOQI2RUPZLRDE4OSDDEL","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":"202656699e4c4384ae7088049bbf5b84b341641e967c7f0e005846055def2524","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-09-21T23:02:42Z","title_canon_sha256":"0e52cecbfbd50dcd46c2fc56cf30ced96750462d5dfb273e616f2143d9d5a79b"},"schema_version":"1.0","source":{"id":"1809.08337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08337","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08337v1","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08337","created_at":"2026-05-18T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"R4QXBDZOQI2R","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R4QXBDZOQI2RUPZL","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R4QXBDZO","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:43e82278325b9c9768a5f9119c35bf424058b852114c338657d038e879c8c2b0","target":"graph","created_at":"2026-05-18T00:05:08Z","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"},"paper":{"abstract_excerpt":"In this paper, a comparison of reinforcement learning algorithms and their performance on a robot box pushing task is provided. The robot box pushing problem is structured as both a single-agent problem and also a multi-agent problem. A Q-learning algorithm is applied to the single-agent box pushing problem, and three different Q-learning algorithms are applied to the multi-agent box pushing problem. Both sets of algorithms are applied on a dynamic environment that is comprised of static objects, a static goal location, a dynamic box location, and dynamic agent positions. A simulation environm","authors_text":"Hung Manh La, Mehdi Rahimi, Spencer Gibb, Yantao Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-09-21T23:02:42Z","title":"A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08337","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":"sha256:74c1a5bbc18ac97e7c869d687ae5755c7a0a848ad95b11a8e345d357e8526a93","target":"record","created_at":"2026-05-18T00:05:08Z","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":"202656699e4c4384ae7088049bbf5b84b341641e967c7f0e005846055def2524","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-09-21T23:02:42Z","title_canon_sha256":"0e52cecbfbd50dcd46c2fc56cf30ced96750462d5dfb273e616f2143d9d5a79b"},"schema_version":"1.0","source":{"id":"1809.08337","kind":"arxiv","version":1}},"canonical_sha256":"8f21708f2e82351a3f2b88c9c7486322d69783e5955418401b79956aea4c34d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f21708f2e82351a3f2b88c9c7486322d69783e5955418401b79956aea4c34d3","first_computed_at":"2026-05-18T00:05:08.769801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:08.769801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCt/gvomX334eUjjw+c+ugZ2nd11Ts3NekxeOMobGt6bA0GwHb+dqOqWPQtPpOpIwXzFgRtVLu4FUeBkIqZsBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:08.770383Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.08337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74c1a5bbc18ac97e7c869d687ae5755c7a0a848ad95b11a8e345d357e8526a93","sha256:43e82278325b9c9768a5f9119c35bf424058b852114c338657d038e879c8c2b0"],"state_sha256":"72d0fcc4b71f84efe2e56ebc578fff98a3f4b97ce76171b303624154c2e11cf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjU1q1rltItDrtK63F10AyvwguBIYZmh8yld/wOqNOmJ+OzAreFk7dx/sUnlHz94DYtLV3i1vqs23zJn0sCYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:00:15.237347Z","bundle_sha256":"5a4939db3e2fa74d97210a9f6e9e8c67082f7b8e39be033aa00da353b1677bf1"}}