{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:J7BBTHFSYMQP6TK52556JU3IFO","short_pith_number":"pith:J7BBTHFS","canonical_record":{"source":{"id":"2004.00980","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-02T13:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"f2d846ee59b0fc877cd9072c6ebc957d7f807ccd96da293e66acde5e1920e7f1","abstract_canon_sha256":"69d2e084d07df92ce1841b978b64cec725ebc052c604ff673af5054cb3c1069f"},"schema_version":"1.0"},"canonical_sha256":"4fc2199cb2c320ff4d5dd77be4d3682b93a4a79ec7b05527656cf66148c32fc4","source":{"kind":"arxiv","id":"2004.00980","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00980","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00980v2","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00980","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"J7BBTHFSYMQP","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"J7BBTHFSYMQP6TK5","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"J7BBTHFS","created_at":"2026-07-05T01:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:J7BBTHFSYMQP6TK52556JU3IFO","target":"record","payload":{"canonical_record":{"source":{"id":"2004.00980","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-02T13:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"f2d846ee59b0fc877cd9072c6ebc957d7f807ccd96da293e66acde5e1920e7f1","abstract_canon_sha256":"69d2e084d07df92ce1841b978b64cec725ebc052c604ff673af5054cb3c1069f"},"schema_version":"1.0"},"canonical_sha256":"4fc2199cb2c320ff4d5dd77be4d3682b93a4a79ec7b05527656cf66148c32fc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:46.238986Z","signature_b64":"05jWQUQrajSp+Gh+spa1LpXPU86o+6cP2XYi8XBD3IYhswZRUIdhl4OMrpsXVqxo/lCzOAMRiP54ArJf5OykCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fc2199cb2c320ff4d5dd77be4d3682b93a4a79ec7b05527656cf66148c32fc4","last_reissued_at":"2026-07-05T01:05:46.238540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:46.238540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.00980","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":"2026-07-05T01:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2egokQKrxpy12LEKhhRo3kiGNfePXwRJ8cm1KOdUygbqTUMpybcvWPlmMXD/b4SogjoL8zCt7rsio4ShHDosCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T23:19:12.822237Z"},"content_sha256":"9f300cef38bf90546177d4ffac03a3d0e65b280d2d4da94e37e1caf5a62c6660","schema_version":"1.0","event_id":"sha256:9f300cef38bf90546177d4ffac03a3d0e65b280d2d4da94e37e1caf5a62c6660"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:J7BBTHFSYMQP6TK52556JU3IFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Space Shaping in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anssi Kanervisto, Christian Scheller, Ville Hautam\\\"aki","submitted_at":"2020-04-02T13:25:55Z","abstract_excerpt":"Reinforcement learning (RL) has been successful in training agents in various learning environments, including video-games. However, such work modifies and shrinks the action space from the game's original. This is to avoid trying \"pointless\" actions and to ease the implementation. Currently, this is mostly done based on intuition, with little systematic research supporting the design decisions. In this work, we aim to gain insight on these action space modifications by conducting extensive experiments in video-game environments. Our results show how domain-specific removal of actions and disc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00980","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/2004.00980/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":"2026-07-05T01:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kzp2ArcViTtq/+X0tnFg1vyaiOjMrYI7NEqE7GoU37Pe4yrtzIo78NhuKG2c68uGz+mlaezhe1wQ0ljnVxldDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T23:19:12.822651Z"},"content_sha256":"935ff1576cc6d214da1675feb94d6bc0c69e4f144c38765ae91404b3d44a1859","schema_version":"1.0","event_id":"sha256:935ff1576cc6d214da1675feb94d6bc0c69e4f144c38765ae91404b3d44a1859"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7BBTHFSYMQP6TK52556JU3IFO/bundle.json","state_url":"https://pith.science/pith/J7BBTHFSYMQP6TK52556JU3IFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7BBTHFSYMQP6TK52556JU3IFO/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":"2026-07-26T23:19:12Z","links":{"resolver":"https://pith.science/pith/J7BBTHFSYMQP6TK52556JU3IFO","bundle":"https://pith.science/pith/J7BBTHFSYMQP6TK52556JU3IFO/bundle.json","state":"https://pith.science/pith/J7BBTHFSYMQP6TK52556JU3IFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7BBTHFSYMQP6TK52556JU3IFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:J7BBTHFSYMQP6TK52556JU3IFO","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":"69d2e084d07df92ce1841b978b64cec725ebc052c604ff673af5054cb3c1069f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-02T13:25:55Z","title_canon_sha256":"f2d846ee59b0fc877cd9072c6ebc957d7f807ccd96da293e66acde5e1920e7f1"},"schema_version":"1.0","source":{"id":"2004.00980","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00980","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00980v2","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00980","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"J7BBTHFSYMQP","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"J7BBTHFSYMQP6TK5","created_at":"2026-07-05T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"J7BBTHFS","created_at":"2026-07-05T01:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:935ff1576cc6d214da1675feb94d6bc0c69e4f144c38765ae91404b3d44a1859","target":"graph","created_at":"2026-07-05T01:05:46Z","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/2004.00980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has been successful in training agents in various learning environments, including video-games. However, such work modifies and shrinks the action space from the game's original. This is to avoid trying \"pointless\" actions and to ease the implementation. Currently, this is mostly done based on intuition, with little systematic research supporting the design decisions. In this work, we aim to gain insight on these action space modifications by conducting extensive experiments in video-game environments. Our results show how domain-specific removal of actions and disc","authors_text":"Anssi Kanervisto, Christian Scheller, Ville Hautam\\\"aki","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-02T13:25:55Z","title":"Action Space Shaping in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00980","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":"sha256:9f300cef38bf90546177d4ffac03a3d0e65b280d2d4da94e37e1caf5a62c6660","target":"record","created_at":"2026-07-05T01:05:46Z","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":"69d2e084d07df92ce1841b978b64cec725ebc052c604ff673af5054cb3c1069f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-02T13:25:55Z","title_canon_sha256":"f2d846ee59b0fc877cd9072c6ebc957d7f807ccd96da293e66acde5e1920e7f1"},"schema_version":"1.0","source":{"id":"2004.00980","kind":"arxiv","version":2}},"canonical_sha256":"4fc2199cb2c320ff4d5dd77be4d3682b93a4a79ec7b05527656cf66148c32fc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fc2199cb2c320ff4d5dd77be4d3682b93a4a79ec7b05527656cf66148c32fc4","first_computed_at":"2026-07-05T01:05:46.238540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:46.238540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"05jWQUQrajSp+Gh+spa1LpXPU86o+6cP2XYi8XBD3IYhswZRUIdhl4OMrpsXVqxo/lCzOAMRiP54ArJf5OykCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:46.238986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.00980","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f300cef38bf90546177d4ffac03a3d0e65b280d2d4da94e37e1caf5a62c6660","sha256:935ff1576cc6d214da1675feb94d6bc0c69e4f144c38765ae91404b3d44a1859"],"state_sha256":"b3f837604e01291b04ab507e5153cb11020d5ce79c5a9f572e1716461808506d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+GgcBolvNJD5B+K1FMUwNHESRXwoCuxLb3pPAfNZxpKuUgW/KpjEAelJ77WmYNhyyWpI4XCy7/WLp8pngKlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T23:19:12.825150Z","bundle_sha256":"905bcf93cacbd8a5529141670d52c6067579658317fef84419557eda618fc19c"}}