{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YNBJEOJLL2FCDFKAPPDYMP5VKB","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":"6548e76c06774b3d466a85efbc5119848731747ff4fbd1b6893c8c308097821e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-09-23T15:23:54Z","title_canon_sha256":"920f73ed1d0886c2c6c23460164b4fa229973cd11960eff3a1ba738296666eed"},"schema_version":"1.0","source":{"id":"2009.11212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.11212","created_at":"2026-07-05T01:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2009.11212v1","created_at":"2026-07-05T01:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11212","created_at":"2026-07-05T01:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"YNBJEOJLL2FC","created_at":"2026-07-05T01:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"YNBJEOJLL2FCDFKA","created_at":"2026-07-05T01:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"YNBJEOJL","created_at":"2026-07-05T01:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:3d6b0867de3a679a22dc478cb6ac7c5437f49320d730188b6cb36ab2acb5947f","target":"graph","created_at":"2026-07-05T01:40:57Z","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/2009.11212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has been successfully used to solve different challenges, e.g. complex board and computer games, recently. However, solving real-world robotics tasks with DRL seems to be a more difficult challenge. The desired approach would be to train the agent in a simulator and transfer it to the real world. Still, models trained in a simulator tend to perform poorly in real-world environments due to the differences. In this paper, we present a DRL-based algorithm that is capable of performing autonomous robot control using Deep Q-Networks (DQN). In our approach, the agen","authors_text":"B\\'alint Gyires-T\\'oth, P\\'eter Alm\\'asi, R\\'obert Moni","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-09-23T15:23:54Z","title":"Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11212","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":"sha256:59390eeae4310046d91546f3ab4ea3925e15141ef950a95cec03d781d652cd0c","target":"record","created_at":"2026-07-05T01:40:57Z","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":"6548e76c06774b3d466a85efbc5119848731747ff4fbd1b6893c8c308097821e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-09-23T15:23:54Z","title_canon_sha256":"920f73ed1d0886c2c6c23460164b4fa229973cd11960eff3a1ba738296666eed"},"schema_version":"1.0","source":{"id":"2009.11212","kind":"arxiv","version":1}},"canonical_sha256":"c34292392b5e8a2195407bc7863fb5506f581a73548d3aef850ea81286cd134b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c34292392b5e8a2195407bc7863fb5506f581a73548d3aef850ea81286cd134b","first_computed_at":"2026-07-05T01:40:57.620484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:57.620484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FFznvZV0a+BlGRlEOoEIXWFugpgCPu/DZ8Bsq5vr+TThKlns19ZlGpI9A/+nR5STlJjHb7iREl1a1YtmCUmQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:57.620882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.11212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59390eeae4310046d91546f3ab4ea3925e15141ef950a95cec03d781d652cd0c","sha256:3d6b0867de3a679a22dc478cb6ac7c5437f49320d730188b6cb36ab2acb5947f"],"state_sha256":"16e2f2527bd8dc43b28f26cd085c4670adc37f6d83476a745f886ff2fc379f28"}