{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:VZTQIUWAIDICSKA7WOVMTAYETX","short_pith_number":"pith:VZTQIUWA","canonical_record":{"source":{"id":"2006.14171","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:47:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a358de2e6557031cf31d1a021fd6787c801f4cdcb0cdb1e7be2b34c7583d4d25","abstract_canon_sha256":"d2ae0698e88b7289499f4c3b1049e7b6e9900d556d48defec2d99c3ce2aa5c8e"},"schema_version":"1.0"},"canonical_sha256":"ae670452c040d029281fb3aac983049dc0466d82b9b4dc2eca3eca289364bb61","source":{"kind":"arxiv","id":"2006.14171","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14171","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14171v3","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14171","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_12","alias_value":"VZTQIUWAIDIC","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"VZTQIUWAIDICSKA7","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"VZTQIUWA","created_at":"2026-07-05T04:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:VZTQIUWAIDICSKA7WOVMTAYETX","target":"record","payload":{"canonical_record":{"source":{"id":"2006.14171","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:47:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a358de2e6557031cf31d1a021fd6787c801f4cdcb0cdb1e7be2b34c7583d4d25","abstract_canon_sha256":"d2ae0698e88b7289499f4c3b1049e7b6e9900d556d48defec2d99c3ce2aa5c8e"},"schema_version":"1.0"},"canonical_sha256":"ae670452c040d029281fb3aac983049dc0466d82b9b4dc2eca3eca289364bb61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:27.204222Z","signature_b64":"uedtAYtNur79OAPDZ38DaEVhjGXEgPTAFk01BcG2WNWpxT76CPaVSRloNPz5RI+eK6W2vKZpAigBm1Y9D7ggBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae670452c040d029281fb3aac983049dc0466d82b9b4dc2eca3eca289364bb61","last_reissued_at":"2026-07-05T04:27:27.203730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:27.203730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.14171","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:27:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZziXdjDp0ucopG2dW8X9qNrEzotzWdpuZvThvSWJFI8dM0MHqqFwAuMhKian/I8BaDgCca2mjgj6g51IPbYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:19:09.233689Z"},"content_sha256":"b675a7ac1a9c63a8dd7584048db78d8c069fd0f52d5b898f205a7d3be0490c28","schema_version":"1.0","event_id":"sha256:b675a7ac1a9c63a8dd7584048db78d8c069fd0f52d5b898f205a7d3be0490c28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:VZTQIUWAIDICSKA7WOVMTAYETX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Santiago Onta\\~n\\'on, Shengyi Huang","submitted_at":"2020-06-25T04:47:09Z","abstract_excerpt":"In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action distribution predicted by the learned policy is likely to be invalid according to the game rules (e.g., walking into a wall). The usual approach to deal with this problem in policy gradient algorithms is to \"mask out\" invalid actions and just sample from the set of valid actions. The implications of this process, however, remain under-investigated. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14171","kind":"arxiv","version":3},"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/2006.14171/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":"2026-07-05T04:27:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Zb5QLpW0c1fdmU2rNzX732Q6wu9Gi6DdhH9nHexDbzTXZlEe5qvh6woMSSoIwc3mwkn9zMEkBa5DTHONby5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:19:09.234700Z"},"content_sha256":"d0616fb847315207c99969581ac580c1e756879dcf20bede7a10472252350ead","schema_version":"1.0","event_id":"sha256:d0616fb847315207c99969581ac580c1e756879dcf20bede7a10472252350ead"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZTQIUWAIDICSKA7WOVMTAYETX/bundle.json","state_url":"https://pith.science/pith/VZTQIUWAIDICSKA7WOVMTAYETX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZTQIUWAIDICSKA7WOVMTAYETX/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":"2026-08-10T20:19:09Z","links":{"resolver":"https://pith.science/pith/VZTQIUWAIDICSKA7WOVMTAYETX","bundle":"https://pith.science/pith/VZTQIUWAIDICSKA7WOVMTAYETX/bundle.json","state":"https://pith.science/pith/VZTQIUWAIDICSKA7WOVMTAYETX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZTQIUWAIDICSKA7WOVMTAYETX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VZTQIUWAIDICSKA7WOVMTAYETX","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":"d2ae0698e88b7289499f4c3b1049e7b6e9900d556d48defec2d99c3ce2aa5c8e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:47:09Z","title_canon_sha256":"a358de2e6557031cf31d1a021fd6787c801f4cdcb0cdb1e7be2b34c7583d4d25"},"schema_version":"1.0","source":{"id":"2006.14171","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14171","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14171v3","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14171","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_12","alias_value":"VZTQIUWAIDIC","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"VZTQIUWAIDICSKA7","created_at":"2026-07-05T04:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"VZTQIUWA","created_at":"2026-07-05T04:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:d0616fb847315207c99969581ac580c1e756879dcf20bede7a10472252350ead","target":"graph","created_at":"2026-07-05T04:27:27Z","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/2006.14171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action distribution predicted by the learned policy is likely to be invalid according to the game rules (e.g., walking into a wall). The usual approach to deal with this problem in policy gradient algorithms is to \"mask out\" invalid actions and just sample from the set of valid actions. The implications of this process, however, remain under-investigated. In this paper, w","authors_text":"Santiago Onta\\~n\\'on, Shengyi Huang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:47:09Z","title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14171","kind":"arxiv","version":3},"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:b675a7ac1a9c63a8dd7584048db78d8c069fd0f52d5b898f205a7d3be0490c28","target":"record","created_at":"2026-07-05T04:27:27Z","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":"d2ae0698e88b7289499f4c3b1049e7b6e9900d556d48defec2d99c3ce2aa5c8e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:47:09Z","title_canon_sha256":"a358de2e6557031cf31d1a021fd6787c801f4cdcb0cdb1e7be2b34c7583d4d25"},"schema_version":"1.0","source":{"id":"2006.14171","kind":"arxiv","version":3}},"canonical_sha256":"ae670452c040d029281fb3aac983049dc0466d82b9b4dc2eca3eca289364bb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae670452c040d029281fb3aac983049dc0466d82b9b4dc2eca3eca289364bb61","first_computed_at":"2026-07-05T04:27:27.203730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:27.203730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uedtAYtNur79OAPDZ38DaEVhjGXEgPTAFk01BcG2WNWpxT76CPaVSRloNPz5RI+eK6W2vKZpAigBm1Y9D7ggBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:27.204222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.14171","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b675a7ac1a9c63a8dd7584048db78d8c069fd0f52d5b898f205a7d3be0490c28","sha256:d0616fb847315207c99969581ac580c1e756879dcf20bede7a10472252350ead"],"state_sha256":"f98a02de571230f5edea8ea221b8de58efecc7ad7cf065bbec40aaf5f81f8e4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0uuLVRTMb/Ghx8yDX1Nwa4bTf2bMkaNoFwVk/RaMivRJcsInPoSOYQlY5E4P3K5b7pRWWnz91uNZt2MJkDFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:19:09.239943Z","bundle_sha256":"0d100ca7491a87e9acd5cd3a9d0eb67e7d71c34275031a8f2768785260c2355f"}}