{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RNHW3J4LAS2RRQZXKP4MESJCGM","short_pith_number":"pith:RNHW3J4L","canonical_record":{"source":{"id":"2309.15484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-27T08:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"631a18a545c934868945b5f0c129ac49c8d1c648b4dd71be7a7b9bcc59566b87","abstract_canon_sha256":"50332b9b32084e5ec60000b15ba7809de924de932479ea4f2f737c4d5edfb624"},"schema_version":"1.0"},"canonical_sha256":"8b4f6da78b04b518c33753f8c24922330b19113c69450dd4a7c1569698dcc747","source":{"kind":"arxiv","id":"2309.15484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15484","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15484v1","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15484","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"RNHW3J4LAS2R","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"RNHW3J4LAS2RRQZX","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"RNHW3J4L","created_at":"2026-07-05T06:54:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RNHW3J4LAS2RRQZXKP4MESJCGM","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-27T08:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"631a18a545c934868945b5f0c129ac49c8d1c648b4dd71be7a7b9bcc59566b87","abstract_canon_sha256":"50332b9b32084e5ec60000b15ba7809de924de932479ea4f2f737c4d5edfb624"},"schema_version":"1.0"},"canonical_sha256":"8b4f6da78b04b518c33753f8c24922330b19113c69450dd4a7c1569698dcc747","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:46.796636Z","signature_b64":"cYYmwFRjV0Q3BC+jdAmbfSLrr3blBSpRjdxgnWNwKnKDFoMfnQ0byk8CGjrNT9bkztemgV9DJF0b8A0LArvvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b4f6da78b04b518c33753f8c24922330b19113c69450dd4a7c1569698dcc747","last_reissued_at":"2026-07-05T06:54:46.796227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:46.796227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15484","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":"2026-07-05T06:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tc6/VJAfQwRijegpX845NI5VXG/GBb76YpSdh82GiqrJCMBdTxn5FZEj7N8VtopZ3+aMM2zDIm4Lt62kzemnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:04:11.223670Z"},"content_sha256":"4af3c500812798bab73739e597e8bfc591efcee5b143996e52e69e7f9ee327c1","schema_version":"1.0","event_id":"sha256:4af3c500812798bab73739e597e8bfc591efcee5b143996e52e69e7f9ee327c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RNHW3J4LAS2RRQZXKP4MESJCGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chiu-Chou Lin, Feng-Jian Wang, I-Chen Wu, Kuo-Hao Ho, Ping-Chun Hsieh, You-Ren Luo","submitted_at":"2023-09-27T08:28:59Z","abstract_excerpt":"In this paper, we propose a new approach called Adaptive Behavioral Costs in Reinforcement Learning (ABC-RL) for training a human-like agent with competitive strength. While deep reinforcement learning agents have recently achieved superhuman performance in various video games, some of these unconstrained agents may exhibit actions, such as shaking and spinning, that are not typically observed in human behavior, resulting in peculiar gameplay experiences. To behave like humans and retain similar performance, ABC-RL augments behavioral limitations as cost signals in reinforcement learning with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15484","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/2309.15484/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":"2026-07-05T06:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6iDH/+K4UphUJ3cMVmbUyElW2VWgdua+LIS4lY1xqFnfxrQZcshtnen3ut8/FJQ+ki7jL3Qx3U0ggBtVhE1WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:04:11.224159Z"},"content_sha256":"bba0e0d3f2e7e3d931a6ab41d94f008f0e9f0055a5d0a25362540017e6c9dc54","schema_version":"1.0","event_id":"sha256:bba0e0d3f2e7e3d931a6ab41d94f008f0e9f0055a5d0a25362540017e6c9dc54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/bundle.json","state_url":"https://pith.science/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/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":"2026-08-03T21:04:11Z","links":{"resolver":"https://pith.science/pith/RNHW3J4LAS2RRQZXKP4MESJCGM","bundle":"https://pith.science/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/bundle.json","state":"https://pith.science/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RNHW3J4LAS2RRQZXKP4MESJCGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RNHW3J4LAS2RRQZXKP4MESJCGM","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":"50332b9b32084e5ec60000b15ba7809de924de932479ea4f2f737c4d5edfb624","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-27T08:28:59Z","title_canon_sha256":"631a18a545c934868945b5f0c129ac49c8d1c648b4dd71be7a7b9bcc59566b87"},"schema_version":"1.0","source":{"id":"2309.15484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15484","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15484v1","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15484","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"RNHW3J4LAS2R","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"RNHW3J4LAS2RRQZX","created_at":"2026-07-05T06:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"RNHW3J4L","created_at":"2026-07-05T06:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:bba0e0d3f2e7e3d931a6ab41d94f008f0e9f0055a5d0a25362540017e6c9dc54","target":"graph","created_at":"2026-07-05T06:54:46Z","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/2309.15484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a new approach called Adaptive Behavioral Costs in Reinforcement Learning (ABC-RL) for training a human-like agent with competitive strength. While deep reinforcement learning agents have recently achieved superhuman performance in various video games, some of these unconstrained agents may exhibit actions, such as shaking and spinning, that are not typically observed in human behavior, resulting in peculiar gameplay experiences. To behave like humans and retain similar performance, ABC-RL augments behavioral limitations as cost signals in reinforcement learning with ","authors_text":"Chiu-Chou Lin, Feng-Jian Wang, I-Chen Wu, Kuo-Hao Ho, Ping-Chun Hsieh, You-Ren Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-27T08:28:59Z","title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15484","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":"sha256:4af3c500812798bab73739e597e8bfc591efcee5b143996e52e69e7f9ee327c1","target":"record","created_at":"2026-07-05T06:54:46Z","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":"50332b9b32084e5ec60000b15ba7809de924de932479ea4f2f737c4d5edfb624","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-27T08:28:59Z","title_canon_sha256":"631a18a545c934868945b5f0c129ac49c8d1c648b4dd71be7a7b9bcc59566b87"},"schema_version":"1.0","source":{"id":"2309.15484","kind":"arxiv","version":1}},"canonical_sha256":"8b4f6da78b04b518c33753f8c24922330b19113c69450dd4a7c1569698dcc747","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b4f6da78b04b518c33753f8c24922330b19113c69450dd4a7c1569698dcc747","first_computed_at":"2026-07-05T06:54:46.796227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:46.796227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cYYmwFRjV0Q3BC+jdAmbfSLrr3blBSpRjdxgnWNwKnKDFoMfnQ0byk8CGjrNT9bkztemgV9DJF0b8A0LArvvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:46.796636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4af3c500812798bab73739e597e8bfc591efcee5b143996e52e69e7f9ee327c1","sha256:bba0e0d3f2e7e3d931a6ab41d94f008f0e9f0055a5d0a25362540017e6c9dc54"],"state_sha256":"484d19bfc3753e92c4e04c5e2c4d232513d391168b7af6c836320cca0dc11a70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DM5gf4cITFpE7p+4uDdOr3t8z2bl+E84PMl2Q/4lWdUq1M88UNM6V5ChPsHsLVfcpNCN5BOS1QP0WeG3qBLgBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:04:11.227686Z","bundle_sha256":"ab7187559815348e83fac72a3105aa019c98ab57262adddfbab614e87c5aded7"}}