{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CMRU6E2MZOF6QGUW2CMYMW3TBM","short_pith_number":"pith:CMRU6E2M","canonical_record":{"source":{"id":"2105.11617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T02:26:01Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"28c351a7482ac9ef44dd7b177326ab88739e5573e830dd34462efb76d90e97a7","abstract_canon_sha256":"ef36f534d981cc06b72171341de7d4ad5a9f946e9d5bc8cef59bd69ff6b99cba"},"schema_version":"1.0"},"canonical_sha256":"13234f134ccb8be81a96d099865b730b13353ce9382918f39e20b8211441b665","source":{"kind":"arxiv","id":"2105.11617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11617","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11617v1","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11617","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"CMRU6E2MZOF6","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"CMRU6E2MZOF6QGUW","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"CMRU6E2M","created_at":"2026-07-05T02:42:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CMRU6E2MZOF6QGUW2CMYMW3TBM","target":"record","payload":{"canonical_record":{"source":{"id":"2105.11617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T02:26:01Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"28c351a7482ac9ef44dd7b177326ab88739e5573e830dd34462efb76d90e97a7","abstract_canon_sha256":"ef36f534d981cc06b72171341de7d4ad5a9f946e9d5bc8cef59bd69ff6b99cba"},"schema_version":"1.0"},"canonical_sha256":"13234f134ccb8be81a96d099865b730b13353ce9382918f39e20b8211441b665","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:54.462027Z","signature_b64":"8z3Dh2QsfyZeI6fbf6jvRjij38qP4Gd9CmqRFvBRXcEfLsgCyudgbxVjeyh7D6FUS8Pv2zgPVUaORU9jRK7vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13234f134ccb8be81a96d099865b730b13353ce9382918f39e20b8211441b665","last_reissued_at":"2026-07-05T02:42:54.461610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:54.461610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.11617","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":"2026-07-05T02:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCWmVmp+8laRL1n5SoIg9TCovSRNGEjo3hw5m1aGGLmQZnnWVKfXBcZ8hy4IyjqPkYTXuoIObU7zpI4YWWO9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T02:22:13.565890Z"},"content_sha256":"9ddb45f58c6be886d1d9f9c8de50abd41a5e16bbb799f3dc0f8c87c86ee80450","schema_version":"1.0","event_id":"sha256:9ddb45f58c6be886d1d9f9c8de50abd41a5e16bbb799f3dc0f8c87c86ee80450"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CMRU6E2MZOF6QGUW2CMYMW3TBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Reward Functions in Q-Learning Applied to a Cart Position Problem","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Amartya Mukherjee","submitted_at":"2021-05-25T02:26:01Z","abstract_excerpt":"Growing advancements in reinforcement learning has led to advancements in control theory. Reinforcement learning has effectively solved the inverted pendulum problem and more recently the double inverted pendulum problem. In reinforcement learning, our agents learn by interacting with the control system with the goal of maximizing rewards. In this paper, we explore three such reward functions in the cart position problem. This paper concludes that a discontinuous reward function that gives non-zero rewards to agents only if they are within a given distance from the desired position gives the b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11617","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.11617/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":"2026-07-05T02:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9V+T0btA/3JWpW8R8tzGs4B+HTF6VX6URIR22nwoGXprgNg4KEMbvlrNf7o3k7z83H/OW0ufZwlIcFWVVgEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T02:22:13.566268Z"},"content_sha256":"ae7bd5c3033cc542286955bc509e52933ed9e61839ac33132e4ad313cf3eaab5","schema_version":"1.0","event_id":"sha256:ae7bd5c3033cc542286955bc509e52933ed9e61839ac33132e4ad313cf3eaab5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/bundle.json","state_url":"https://pith.science/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/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":"2026-07-16T02:22:13Z","links":{"resolver":"https://pith.science/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM","bundle":"https://pith.science/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/bundle.json","state":"https://pith.science/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMRU6E2MZOF6QGUW2CMYMW3TBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CMRU6E2MZOF6QGUW2CMYMW3TBM","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":"ef36f534d981cc06b72171341de7d4ad5a9f946e9d5bc8cef59bd69ff6b99cba","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T02:26:01Z","title_canon_sha256":"28c351a7482ac9ef44dd7b177326ab88739e5573e830dd34462efb76d90e97a7"},"schema_version":"1.0","source":{"id":"2105.11617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11617","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11617v1","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11617","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"CMRU6E2MZOF6","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"CMRU6E2MZOF6QGUW","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"CMRU6E2M","created_at":"2026-07-05T02:42:54Z"}],"graph_snapshots":[{"event_id":"sha256:ae7bd5c3033cc542286955bc509e52933ed9e61839ac33132e4ad313cf3eaab5","target":"graph","created_at":"2026-07-05T02:42:54Z","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/2105.11617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Growing advancements in reinforcement learning has led to advancements in control theory. Reinforcement learning has effectively solved the inverted pendulum problem and more recently the double inverted pendulum problem. In reinforcement learning, our agents learn by interacting with the control system with the goal of maximizing rewards. In this paper, we explore three such reward functions in the cart position problem. This paper concludes that a discontinuous reward function that gives non-zero rewards to agents only if they are within a given distance from the desired position gives the b","authors_text":"Amartya Mukherjee","cross_cats":["cs.AI","cs.RO","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T02:26:01Z","title":"A Comparison of Reward Functions in Q-Learning Applied to a Cart Position Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11617","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":"sha256:9ddb45f58c6be886d1d9f9c8de50abd41a5e16bbb799f3dc0f8c87c86ee80450","target":"record","created_at":"2026-07-05T02:42:54Z","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":"ef36f534d981cc06b72171341de7d4ad5a9f946e9d5bc8cef59bd69ff6b99cba","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T02:26:01Z","title_canon_sha256":"28c351a7482ac9ef44dd7b177326ab88739e5573e830dd34462efb76d90e97a7"},"schema_version":"1.0","source":{"id":"2105.11617","kind":"arxiv","version":1}},"canonical_sha256":"13234f134ccb8be81a96d099865b730b13353ce9382918f39e20b8211441b665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13234f134ccb8be81a96d099865b730b13353ce9382918f39e20b8211441b665","first_computed_at":"2026-07-05T02:42:54.461610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:54.461610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8z3Dh2QsfyZeI6fbf6jvRjij38qP4Gd9CmqRFvBRXcEfLsgCyudgbxVjeyh7D6FUS8Pv2zgPVUaORU9jRK7vAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:54.462027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ddb45f58c6be886d1d9f9c8de50abd41a5e16bbb799f3dc0f8c87c86ee80450","sha256:ae7bd5c3033cc542286955bc509e52933ed9e61839ac33132e4ad313cf3eaab5"],"state_sha256":"bd878cf04c2fd0d8dda8ef426f48122794ab2e5f3db6f5078955f9d29ad12392"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+WtG3Bg5Gq4qxQLBBh6lVPLzwLCgZgkHWqRcfPH7Mdq/y6fqgPLyCOoyG11XGCSphJ58LLtXOS92tkO7gGhAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T02:22:13.568466Z","bundle_sha256":"65086c7725d3eb09c06975df4d2f0e33101c4d08785292fc9954a167fff2443c"}}