{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7PZSRZD2XIC6DFCIMTIFMN4FWQ","short_pith_number":"pith:7PZSRZD2","canonical_record":{"source":{"id":"1907.11788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-26T20:36:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2c219519f0f6d0102b4ddce67af1ef21f49a020d4237cf5b1fdc67a074dc0027","abstract_canon_sha256":"4b465b76897e5a54fd7fbe81de86e07391e33fcbf881c16ead1d17f609120275"},"schema_version":"1.0"},"canonical_sha256":"fbf328e47aba05e1944864d0563785b4175b4342e1efe0a4a2ad09a88dd27688","source":{"kind":"arxiv","id":"1907.11788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11788","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11788v1","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11788","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"7PZSRZD2XIC6","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7PZSRZD2XIC6DFCI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7PZSRZD2","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7PZSRZD2XIC6DFCIMTIFMN4FWQ","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-26T20:36:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2c219519f0f6d0102b4ddce67af1ef21f49a020d4237cf5b1fdc67a074dc0027","abstract_canon_sha256":"4b465b76897e5a54fd7fbe81de86e07391e33fcbf881c16ead1d17f609120275"},"schema_version":"1.0"},"canonical_sha256":"fbf328e47aba05e1944864d0563785b4175b4342e1efe0a4a2ad09a88dd27688","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:23.058690Z","signature_b64":"AVT0yCxx6eEhQVenDZRTo5wdCTUslg/7v/tmoeKkYW2HasqpRd+wYkwjPxsQFA/Mcw4unU7JuZdgLRXgH+wWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbf328e47aba05e1944864d0563785b4175b4342e1efe0a4a2ad09a88dd27688","last_reissued_at":"2026-05-17T23:39:23.057744Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:23.057744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11788","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":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxsqUE7EsjtY7OQ9pbKsH5UZKVQ3AutmddymdCtH5p37fLXTuuHJusMEQfH6X3Mvc/D6igpO/Zd0m2PUWK9cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T09:53:44.776005Z"},"content_sha256":"8af1e9865475ad694763cd26112503ffdced92b556951a2a96594b8a763508fc","schema_version":"1.0","event_id":"sha256:8af1e9865475ad694763cd26112503ffdced92b556951a2a96594b8a763508fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7PZSRZD2XIC6DFCIMTIFMN4FWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bilal Kartal, Chao Gao, Matthew E. Taylor, Pablo Hernandez-Leal","submitted_at":"2019-07-26T20:36:09Z","abstract_excerpt":"How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for RL --- past work has shown that model-free RL algorithms fail to achieve significant learning without artificially reducing the environment's complexity. In this paper, we illuminate reasons behind this failure by providing a thorough analysis on the hardness of random exploration in Pommerman. While model-free random exploration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11788","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ZEK1Xef83Z84rPQy2O0CsKZLaJHT4NcNImctE9rJMXrdqTxWsRnzRZ45P4K1IbTd/tEhcaDzmr194VWNECTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T09:53:44.776792Z"},"content_sha256":"64f299fcfaaa3f59165ef38400dcaa63cf95e5e6d1685c11e910c75d98da4aef","schema_version":"1.0","event_id":"sha256:64f299fcfaaa3f59165ef38400dcaa63cf95e5e6d1685c11e910c75d98da4aef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/bundle.json","state_url":"https://pith.science/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/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":"2026-05-23T09:53:44Z","links":{"resolver":"https://pith.science/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ","bundle":"https://pith.science/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/bundle.json","state":"https://pith.science/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7PZSRZD2XIC6DFCIMTIFMN4FWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7PZSRZD2XIC6DFCIMTIFMN4FWQ","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":"4b465b76897e5a54fd7fbe81de86e07391e33fcbf881c16ead1d17f609120275","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-26T20:36:09Z","title_canon_sha256":"2c219519f0f6d0102b4ddce67af1ef21f49a020d4237cf5b1fdc67a074dc0027"},"schema_version":"1.0","source":{"id":"1907.11788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11788","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11788v1","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11788","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"7PZSRZD2XIC6","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7PZSRZD2XIC6DFCI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7PZSRZD2","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:64f299fcfaaa3f59165ef38400dcaa63cf95e5e6d1685c11e910c75d98da4aef","target":"graph","created_at":"2026-05-17T23:39:23Z","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"},"paper":{"abstract_excerpt":"How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for RL --- past work has shown that model-free RL algorithms fail to achieve significant learning without artificially reducing the environment's complexity. In this paper, we illuminate reasons behind this failure by providing a thorough analysis on the hardness of random exploration in Pommerman. While model-free random exploration","authors_text":"Bilal Kartal, Chao Gao, Matthew E. Taylor, Pablo Hernandez-Leal","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-26T20:36:09Z","title":"On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11788","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":"sha256:8af1e9865475ad694763cd26112503ffdced92b556951a2a96594b8a763508fc","target":"record","created_at":"2026-05-17T23:39:23Z","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":"4b465b76897e5a54fd7fbe81de86e07391e33fcbf881c16ead1d17f609120275","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-26T20:36:09Z","title_canon_sha256":"2c219519f0f6d0102b4ddce67af1ef21f49a020d4237cf5b1fdc67a074dc0027"},"schema_version":"1.0","source":{"id":"1907.11788","kind":"arxiv","version":1}},"canonical_sha256":"fbf328e47aba05e1944864d0563785b4175b4342e1efe0a4a2ad09a88dd27688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbf328e47aba05e1944864d0563785b4175b4342e1efe0a4a2ad09a88dd27688","first_computed_at":"2026-05-17T23:39:23.057744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:23.057744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AVT0yCxx6eEhQVenDZRTo5wdCTUslg/7v/tmoeKkYW2HasqpRd+wYkwjPxsQFA/Mcw4unU7JuZdgLRXgH+wWCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:23.058690Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8af1e9865475ad694763cd26112503ffdced92b556951a2a96594b8a763508fc","sha256:64f299fcfaaa3f59165ef38400dcaa63cf95e5e6d1685c11e910c75d98da4aef"],"state_sha256":"86778f7517a38819461e53a80462aa563d9765fa68b82865815c318a68c4c49d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PVxRH8XRj9QOaJZpkvWKS23mYa6LUTsO6h1GvUIOJoySolcw+bu2AjONm3zZoVJ5KyQqJoX8/58fT3NRqJBIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T09:53:44.780821Z","bundle_sha256":"afa18b6db79a989e425e77b443c71e6c959f3149c861a81903874469b3565a3e"}}