{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:THKEN6LXE7X5VXEW33VS3YJ7TG","short_pith_number":"pith:THKEN6LX","canonical_record":{"source":{"id":"2111.02552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T22:45:55Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"6ab3f2b7483a621b89d64654ff62e1983b8a27dc2d169c1f3979996301331bf0","abstract_canon_sha256":"80dafc64bdb8a9fb19fdfb7fff8f5e128f08ef1fdb1e0017c7188ee184a44add"},"schema_version":"1.0"},"canonical_sha256":"99d446f97727efdadc96deeb2de13f99860bca095002a97d07d546f38d8ffa2b","source":{"kind":"arxiv","id":"2111.02552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02552","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02552v1","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02552","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"THKEN6LXE7X5","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"THKEN6LXE7X5VXEW","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"THKEN6LX","created_at":"2026-07-05T03:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:THKEN6LXE7X5VXEW33VS3YJ7TG","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T22:45:55Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"6ab3f2b7483a621b89d64654ff62e1983b8a27dc2d169c1f3979996301331bf0","abstract_canon_sha256":"80dafc64bdb8a9fb19fdfb7fff8f5e128f08ef1fdb1e0017c7188ee184a44add"},"schema_version":"1.0"},"canonical_sha256":"99d446f97727efdadc96deeb2de13f99860bca095002a97d07d546f38d8ffa2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:05.713286Z","signature_b64":"GkqGkBlMUdTOc6dZvLMKD+ZfuHmf5jskRFKEQfag0yNbf0yFnGBVFh3818CJGse5oTeWE5i72KZdOhGHf/jUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d446f97727efdadc96deeb2de13f99860bca095002a97d07d546f38d8ffa2b","last_reissued_at":"2026-07-05T03:29:05.712765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:05.712765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02552","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":"2026-07-05T03:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8DTfkMaJz+F1RYkW5IbFfl8M7MGjjBtkGQUuhhIH8nkzrq/ZrdCbds7XlILKWvLpgvhXy4QE1RUlQyOPb7PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:55.879831Z"},"content_sha256":"9a786749e4b92f6f0fd09381a6984a8888a6425d94c02d1bf74aacf1d078f7bb","schema_version":"1.0","event_id":"sha256:9a786749e4b92f6f0fd09381a6984a8888a6425d94c02d1bf74aacf1d078f7bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:THKEN6LXE7X5VXEW33VS3YJ7TG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bartolomeo Stellato, Daniela Rus, Igor Gilitschenski, Markus Wulfmeier, Martin Riedmiller, Tim Seyde, Wilko Schwarting","submitted_at":"2021-11-03T22:45:55Z","abstract_excerpt":"Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space. In this work, we investigate the colloquially known phenomenon that trained agents often prefer actions at the boundaries of that space. We draw theoretical connections to the emergence of bang-bang behavior in optimal control, and provide extensive empirical evaluation across a variety of recent RL algorithms. We replace the normal Gaussian by a Bernoulli distribution that solely considers the extremes along each action dimension - a bang-bang controller. Surprising"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02552","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/2111.02552/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":"2026-07-05T03:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QX/XOctBPSkdox7Fy9ApQj/c76o///toLNIq85QoLLg/tIvSxID8pu8JePdejzNaXCiYhBnj7kBMlf0vMY+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:55.880733Z"},"content_sha256":"b57bc70eaee6efd4f0cfebf6bc0f825de85677cb30acc7dd1176f50af1d9faca","schema_version":"1.0","event_id":"sha256:b57bc70eaee6efd4f0cfebf6bc0f825de85677cb30acc7dd1176f50af1d9faca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/bundle.json","state_url":"https://pith.science/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/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":"2026-08-04T17:30:55Z","links":{"resolver":"https://pith.science/pith/THKEN6LXE7X5VXEW33VS3YJ7TG","bundle":"https://pith.science/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/bundle.json","state":"https://pith.science/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THKEN6LXE7X5VXEW33VS3YJ7TG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:THKEN6LXE7X5VXEW33VS3YJ7TG","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":"80dafc64bdb8a9fb19fdfb7fff8f5e128f08ef1fdb1e0017c7188ee184a44add","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T22:45:55Z","title_canon_sha256":"6ab3f2b7483a621b89d64654ff62e1983b8a27dc2d169c1f3979996301331bf0"},"schema_version":"1.0","source":{"id":"2111.02552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02552","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02552v1","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02552","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"THKEN6LXE7X5","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"THKEN6LXE7X5VXEW","created_at":"2026-07-05T03:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"THKEN6LX","created_at":"2026-07-05T03:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:b57bc70eaee6efd4f0cfebf6bc0f825de85677cb30acc7dd1176f50af1d9faca","target":"graph","created_at":"2026-07-05T03:29:05Z","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/2111.02552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space. In this work, we investigate the colloquially known phenomenon that trained agents often prefer actions at the boundaries of that space. We draw theoretical connections to the emergence of bang-bang behavior in optimal control, and provide extensive empirical evaluation across a variety of recent RL algorithms. We replace the normal Gaussian by a Bernoulli distribution that solely considers the extremes along each action dimension - a bang-bang controller. Surprising","authors_text":"Bartolomeo Stellato, Daniela Rus, Igor Gilitschenski, Markus Wulfmeier, Martin Riedmiller, Tim Seyde, Wilko Schwarting","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T22:45:55Z","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02552","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":"sha256:9a786749e4b92f6f0fd09381a6984a8888a6425d94c02d1bf74aacf1d078f7bb","target":"record","created_at":"2026-07-05T03:29:05Z","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":"80dafc64bdb8a9fb19fdfb7fff8f5e128f08ef1fdb1e0017c7188ee184a44add","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T22:45:55Z","title_canon_sha256":"6ab3f2b7483a621b89d64654ff62e1983b8a27dc2d169c1f3979996301331bf0"},"schema_version":"1.0","source":{"id":"2111.02552","kind":"arxiv","version":1}},"canonical_sha256":"99d446f97727efdadc96deeb2de13f99860bca095002a97d07d546f38d8ffa2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99d446f97727efdadc96deeb2de13f99860bca095002a97d07d546f38d8ffa2b","first_computed_at":"2026-07-05T03:29:05.712765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:05.712765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkqGkBlMUdTOc6dZvLMKD+ZfuHmf5jskRFKEQfag0yNbf0yFnGBVFh3818CJGse5oTeWE5i72KZdOhGHf/jUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:05.713286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a786749e4b92f6f0fd09381a6984a8888a6425d94c02d1bf74aacf1d078f7bb","sha256:b57bc70eaee6efd4f0cfebf6bc0f825de85677cb30acc7dd1176f50af1d9faca"],"state_sha256":"7b6ab310f60f8130f10ff6129f6a76c45a36aff17d3f6251322e5e83462c5243"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M49UZ3URF2R3EXHCmQ7NtaaKnGhPJKG8L/fbu8zQ/2/V6r5yQ29Mk5uyCs4KpmL49f3p/HvIJxBKcVoJlS+XCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:30:55.892232Z","bundle_sha256":"2d11afad9e2ee07a77d77c3e3df0e260f6593842e2667d4987003f8859f0a07a"}}