{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QPI4Z6WYIFAW4CXKN7KLUSSF42","short_pith_number":"pith:QPI4Z6WY","canonical_record":{"source":{"id":"2306.08008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T09:13:13Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5573d1d98c555a34ae4f7a94cabacb074c91c426de70bb6d68586c2e929fdd97","abstract_canon_sha256":"43248cc2693f6517034574be519b51253dc61c94b0462a3b524bee1039bae0bc"},"schema_version":"1.0"},"canonical_sha256":"83d1ccfad841416e0aea6fd4ba4a45e6835361385df576974f000299d1b5f3dd","source":{"kind":"arxiv","id":"2306.08008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08008","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08008v1","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08008","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_12","alias_value":"QPI4Z6WYIFAW","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_16","alias_value":"QPI4Z6WYIFAW4CXK","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_8","alias_value":"QPI4Z6WY","created_at":"2026-07-05T06:20:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QPI4Z6WYIFAW4CXKN7KLUSSF42","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T09:13:13Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5573d1d98c555a34ae4f7a94cabacb074c91c426de70bb6d68586c2e929fdd97","abstract_canon_sha256":"43248cc2693f6517034574be519b51253dc61c94b0462a3b524bee1039bae0bc"},"schema_version":"1.0"},"canonical_sha256":"83d1ccfad841416e0aea6fd4ba4a45e6835361385df576974f000299d1b5f3dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:46.615177Z","signature_b64":"CxolHDr02golTylmftVNvdoAkpQvjsqyyJ32ijwRWd3tc1aVONBskust1r+2xM84YVBJLaF2egkFOxKOacbnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d1ccfad841416e0aea6fd4ba4a45e6835361385df576974f000299d1b5f3dd","last_reissued_at":"2026-07-05T06:20:46.614759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:46.614759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08008","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":"2026-07-05T06:20:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5qpeE2Qq25YGM9DLwj+M2KxLBD/cRS/r8S6lGXVxW7HyPGysGzEywpSQcgKQsok60EpxIkjL2KfAdPxUHQRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:41.355952Z"},"content_sha256":"3d1cea159d4afa4397dd51530377b03f1e8a729beefef74bf6620d915714dc74","schema_version":"1.0","event_id":"sha256:3d1cea159d4afa4397dd51530377b03f1e8a729beefef74bf6620d915714dc74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QPI4Z6WYIFAW4CXKN7KLUSSF42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Interval Restrictions on Action Spaces in Deep Reinforcement Learning for Obstacle Avoidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Tim Grams","submitted_at":"2023-06-13T09:13:13Z","abstract_excerpt":"Deep reinforcement learning algorithms typically act on the same set of actions. However, this is not sufficient for a wide range of real-world applications where different subsets are available at each step. In this thesis, we consider the problem of interval restrictions as they occur in pathfinding with dynamic obstacles. When actions that lead to collisions are avoided, the continuous action space is split into variable parts. Recent research learns with strong assumptions on the number of intervals, is limited to convex subsets, and the available actions are learned from the observations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08008","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/2306.08008/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":"2026-07-05T06:20:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+7ZsmjV0dNQnKBdqhFxIo5M+Q2k+Nkq5WBX5sV7d/IoxcgOL8TeiQgUSEN0b0ZE6ZVA0q7eZ19at8K4NH6mCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:41.356526Z"},"content_sha256":"f0c74b6d9825fc7a84dc29c6e1ecec0adf59a29827fec81f9dc57c311390d56f","schema_version":"1.0","event_id":"sha256:f0c74b6d9825fc7a84dc29c6e1ecec0adf59a29827fec81f9dc57c311390d56f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/bundle.json","state_url":"https://pith.science/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/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":"2026-08-08T03:09:41Z","links":{"resolver":"https://pith.science/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42","bundle":"https://pith.science/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/bundle.json","state":"https://pith.science/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPI4Z6WYIFAW4CXKN7KLUSSF42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QPI4Z6WYIFAW4CXKN7KLUSSF42","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":"43248cc2693f6517034574be519b51253dc61c94b0462a3b524bee1039bae0bc","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T09:13:13Z","title_canon_sha256":"5573d1d98c555a34ae4f7a94cabacb074c91c426de70bb6d68586c2e929fdd97"},"schema_version":"1.0","source":{"id":"2306.08008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08008","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08008v1","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08008","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_12","alias_value":"QPI4Z6WYIFAW","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_16","alias_value":"QPI4Z6WYIFAW4CXK","created_at":"2026-07-05T06:20:46Z"},{"alias_kind":"pith_short_8","alias_value":"QPI4Z6WY","created_at":"2026-07-05T06:20:46Z"}],"graph_snapshots":[{"event_id":"sha256:f0c74b6d9825fc7a84dc29c6e1ecec0adf59a29827fec81f9dc57c311390d56f","target":"graph","created_at":"2026-07-05T06:20:46Z","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/2306.08008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning algorithms typically act on the same set of actions. However, this is not sufficient for a wide range of real-world applications where different subsets are available at each step. In this thesis, we consider the problem of interval restrictions as they occur in pathfinding with dynamic obstacles. When actions that lead to collisions are avoided, the continuous action space is split into variable parts. Recent research learns with strong assumptions on the number of intervals, is limited to convex subsets, and the available actions are learned from the observations.","authors_text":"Tim Grams","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T09:13:13Z","title":"Dynamic Interval Restrictions on Action Spaces in Deep Reinforcement Learning for Obstacle Avoidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08008","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":"sha256:3d1cea159d4afa4397dd51530377b03f1e8a729beefef74bf6620d915714dc74","target":"record","created_at":"2026-07-05T06:20:46Z","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":"43248cc2693f6517034574be519b51253dc61c94b0462a3b524bee1039bae0bc","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T09:13:13Z","title_canon_sha256":"5573d1d98c555a34ae4f7a94cabacb074c91c426de70bb6d68586c2e929fdd97"},"schema_version":"1.0","source":{"id":"2306.08008","kind":"arxiv","version":1}},"canonical_sha256":"83d1ccfad841416e0aea6fd4ba4a45e6835361385df576974f000299d1b5f3dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83d1ccfad841416e0aea6fd4ba4a45e6835361385df576974f000299d1b5f3dd","first_computed_at":"2026-07-05T06:20:46.614759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:46.614759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CxolHDr02golTylmftVNvdoAkpQvjsqyyJ32ijwRWd3tc1aVONBskust1r+2xM84YVBJLaF2egkFOxKOacbnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:46.615177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d1cea159d4afa4397dd51530377b03f1e8a729beefef74bf6620d915714dc74","sha256:f0c74b6d9825fc7a84dc29c6e1ecec0adf59a29827fec81f9dc57c311390d56f"],"state_sha256":"f0a74976acda1e957cb99e38ab487295d876369e22ddd82b4b7290e8688223fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"44Uht1YD/rcyzeZrtce4bLZ9EweYG+UOvTXvwuJ/UaeBd+iAjXZoB6V0tDTVPHlv5cTf7q3KWq3j2K2YsUPHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:09:41.361040Z","bundle_sha256":"a0e5d3297b35246d31c9e5adff852cb3cf338483b4778e8a1b616b69ffd5f08f"}}