{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2FOEPY3DS2OQFG6JXYXNY5IZPA","short_pith_number":"pith:2FOEPY3D","schema_version":"1.0","canonical_sha256":"d15c47e363969d029bc9be2edc7519781a7b30d2980bd397a32a2b09c90d717d","source":{"kind":"arxiv","id":"1904.05759","version":1},"attestation_state":"computed","paper":{"title":"Safer Deep RL with Shallow MCTS: A Case Study in Pommerman","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bilal Kartal, Chao Gao, Matthew E. Taylor, Pablo Hernandez-Leal","submitted_at":"2019-04-10T14:34:40Z","abstract_excerpt":"Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for reinforcement learning (RL) --- past work has shown that model-free RL algorithms fail to achieve significant learning. In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic eve"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.05759","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-10T14:34:40Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ce568e5af37dd89831409247d37ba9946cedfcb9d26f85b0d925714583313c5b","abstract_canon_sha256":"fd949ba2d1bfb5f25635a2807b58a236d585a43d952024acaab81509b064f7f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:48.557478Z","signature_b64":"Fe0kd9csxJEZV1fFmLmeBBWWQ8FIUHWEivfy6aIQur+ruiuAztTaOSB2f/4azWJIJbA4s5eS67x+7xqlamU8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d15c47e363969d029bc9be2edc7519781a7b30d2980bd397a32a2b09c90d717d","last_reissued_at":"2026-05-17T23:48:48.556997Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:48.556997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safer Deep RL with Shallow MCTS: A Case Study in Pommerman","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bilal Kartal, Chao Gao, Matthew E. Taylor, Pablo Hernandez-Leal","submitted_at":"2019-04-10T14:34:40Z","abstract_excerpt":"Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for reinforcement learning (RL) --- past work has shown that model-free RL algorithms fail to achieve significant learning. In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic eve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05759","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.05759","created_at":"2026-05-17T23:48:48.557067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05759v1","created_at":"2026-05-17T23:48:48.557067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05759","created_at":"2026-05-17T23:48:48.557067+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FOEPY3DS2OQ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FOEPY3DS2OQFG6J","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FOEPY3D","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10124","citing_title":"On Multi-Agent Learning in Team Sports Games","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA","json":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA.json","graph_json":"https://pith.science/api/pith-number/2FOEPY3DS2OQFG6JXYXNY5IZPA/graph.json","events_json":"https://pith.science/api/pith-number/2FOEPY3DS2OQFG6JXYXNY5IZPA/events.json","paper":"https://pith.science/paper/2FOEPY3D"},"agent_actions":{"view_html":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA","download_json":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA.json","view_paper":"https://pith.science/paper/2FOEPY3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05759&json=true","fetch_graph":"https://pith.science/api/pith-number/2FOEPY3DS2OQFG6JXYXNY5IZPA/graph.json","fetch_events":"https://pith.science/api/pith-number/2FOEPY3DS2OQFG6JXYXNY5IZPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA/action/storage_attestation","attest_author":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA/action/author_attestation","sign_citation":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA/action/citation_signature","submit_replication":"https://pith.science/pith/2FOEPY3DS2OQFG6JXYXNY5IZPA/action/replication_record"}},"created_at":"2026-05-17T23:48:48.557067+00:00","updated_at":"2026-05-17T23:48:48.557067+00:00"}