{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:H2KM56DCYCJMY2MR2Q5UCTHIBY","short_pith_number":"pith:H2KM56DC","canonical_record":{"source":{"id":"1602.04936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-02-16T08:17:17Z","cross_cats_sorted":[],"title_canon_sha256":"f3ac8f5ae6342775970accb52e56f097b1133e80c3c9e7f6a84a35fcc96144c5","abstract_canon_sha256":"5cc4fe92aff259f181b0bd190e70ab2f2f8268a6f3a956dfca3a13a4b75f462b"},"schema_version":"1.0"},"canonical_sha256":"3e94cef862c092cc6991d43b414ce80e1ff0392797fc70934252d8b5bdd94a41","source":{"kind":"arxiv","id":"1602.04936","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.04936","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"1602.04936v1","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04936","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"H2KM56DCYCJM","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"H2KM56DCYCJMY2MR","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"H2KM56DC","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:H2KM56DCYCJMY2MR2Q5UCTHIBY","target":"record","payload":{"canonical_record":{"source":{"id":"1602.04936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-02-16T08:17:17Z","cross_cats_sorted":[],"title_canon_sha256":"f3ac8f5ae6342775970accb52e56f097b1133e80c3c9e7f6a84a35fcc96144c5","abstract_canon_sha256":"5cc4fe92aff259f181b0bd190e70ab2f2f8268a6f3a956dfca3a13a4b75f462b"},"schema_version":"1.0"},"canonical_sha256":"3e94cef862c092cc6991d43b414ce80e1ff0392797fc70934252d8b5bdd94a41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:37.822691Z","signature_b64":"BP3ivtzaiKD5J9doLZRzd04xgAqyqKqYsMi3EWeyDXWFcWgUCqfG086DJzce9Z+xt7EHqXMz6V1/AXRWGctFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e94cef862c092cc6991d43b414ce80e1ff0392797fc70934252d8b5bdd94a41","last_reissued_at":"2026-05-18T01:20:37.822313Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:37.822313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.04936","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":"2026-05-18T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8e2tPMJ3qUpWzXnoPiwHI//UGiVB0xzoq1eyCTPQ3+Odh0TLPWS09ZH+Gg3KQROrKw18XkVNV7cj9tRh35cBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:14:07.747405Z"},"content_sha256":"c60eb8dd7c70b712e33be4852b9989f402af52ba98a12b8afd120bb51cf80290","schema_version":"1.0","event_id":"sha256:c60eb8dd7c70b712e33be4852b9989f402af52ba98a12b8afd120bb51cf80290"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:H2KM56DCYCJMY2MR2Q5UCTHIBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning approach for Real Time Strategy Games Battle city and S3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amit Patel, Harshit Sethy","submitted_at":"2016-02-16T08:17:17Z","abstract_excerpt":"In this paper we proposed reinforcement learning algorithms with the generalized reward function. In our proposed method we use Q-learning and SARSA algorithms with generalised reward function to train the reinforcement learning agent. We evaluated the performance of our proposed algorithms on two real-time strategy games called BattleCity and S3. There are two main advantages of having such an approach as compared to other works in RTS. (1) We can ignore the concept of a simulator which is often game specific and is usually hard coded in any type of RTS games (2) our system can learn from int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04936","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":"2026-05-18T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wZqFB5nEe7Dqwm1GT49wnd+BUgC0x/i4IH4UEQeUjb2CP5MZTza4vbTZtJqa4mN55HbTCmDn6uJxrl3RQC5/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:14:07.748121Z"},"content_sha256":"512cade49e6e5fd1cc0bf845e3e5744ccaf59f518314f6dc4179ac09b79674d5","schema_version":"1.0","event_id":"sha256:512cade49e6e5fd1cc0bf845e3e5744ccaf59f518314f6dc4179ac09b79674d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/bundle.json","state_url":"https://pith.science/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/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":"2026-06-09T09:14:07Z","links":{"resolver":"https://pith.science/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY","bundle":"https://pith.science/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/bundle.json","state":"https://pith.science/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2KM56DCYCJMY2MR2Q5UCTHIBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:H2KM56DCYCJMY2MR2Q5UCTHIBY","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":"5cc4fe92aff259f181b0bd190e70ab2f2f8268a6f3a956dfca3a13a4b75f462b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-02-16T08:17:17Z","title_canon_sha256":"f3ac8f5ae6342775970accb52e56f097b1133e80c3c9e7f6a84a35fcc96144c5"},"schema_version":"1.0","source":{"id":"1602.04936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.04936","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"1602.04936v1","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04936","created_at":"2026-05-18T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"H2KM56DCYCJM","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"H2KM56DCYCJMY2MR","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"H2KM56DC","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:512cade49e6e5fd1cc0bf845e3e5744ccaf59f518314f6dc4179ac09b79674d5","target":"graph","created_at":"2026-05-18T01:20:37Z","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":"In this paper we proposed reinforcement learning algorithms with the generalized reward function. In our proposed method we use Q-learning and SARSA algorithms with generalised reward function to train the reinforcement learning agent. We evaluated the performance of our proposed algorithms on two real-time strategy games called BattleCity and S3. There are two main advantages of having such an approach as compared to other works in RTS. (1) We can ignore the concept of a simulator which is often game specific and is usually hard coded in any type of RTS games (2) our system can learn from int","authors_text":"Amit Patel, Harshit Sethy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-02-16T08:17:17Z","title":"Reinforcement Learning approach for Real Time Strategy Games Battle city and S3"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04936","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:c60eb8dd7c70b712e33be4852b9989f402af52ba98a12b8afd120bb51cf80290","target":"record","created_at":"2026-05-18T01:20:37Z","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":"5cc4fe92aff259f181b0bd190e70ab2f2f8268a6f3a956dfca3a13a4b75f462b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-02-16T08:17:17Z","title_canon_sha256":"f3ac8f5ae6342775970accb52e56f097b1133e80c3c9e7f6a84a35fcc96144c5"},"schema_version":"1.0","source":{"id":"1602.04936","kind":"arxiv","version":1}},"canonical_sha256":"3e94cef862c092cc6991d43b414ce80e1ff0392797fc70934252d8b5bdd94a41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e94cef862c092cc6991d43b414ce80e1ff0392797fc70934252d8b5bdd94a41","first_computed_at":"2026-05-18T01:20:37.822313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:37.822313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BP3ivtzaiKD5J9doLZRzd04xgAqyqKqYsMi3EWeyDXWFcWgUCqfG086DJzce9Z+xt7EHqXMz6V1/AXRWGctFBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:37.822691Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.04936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c60eb8dd7c70b712e33be4852b9989f402af52ba98a12b8afd120bb51cf80290","sha256:512cade49e6e5fd1cc0bf845e3e5744ccaf59f518314f6dc4179ac09b79674d5"],"state_sha256":"34b48175e510e221577c7253a1fe6b0c29882c76323a421965aa0a45dc3b84b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAUjuhHsDGqedZ8lO9FQI2pl/N2vpOFxS+6ZcDvtDG4KfBFl1nIWXbQspeTMOsL3XDwX2PpSnWxb9sMf/baSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:14:07.752565Z","bundle_sha256":"f79abdd7e506777d1fbcfa05374af5de1f95a11446ef152378d470d5b639a075"}}