{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZYOEDSTBXFTGHY4CG66F2ANAKP","short_pith_number":"pith:ZYOEDSTB","canonical_record":{"source":{"id":"1905.00741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T13:42:51Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fc0e1b10b85501b455cb361fa1cd93db9fc246e86ad864d46e4ba0f793612ce0","abstract_canon_sha256":"dd7d687b36e4548a5a00389ffff5ed3ec549b599248123d76ef1690b1022a0db"},"schema_version":"1.0"},"canonical_sha256":"ce1c41ca61b96663e38237bc5d01a053c6dee447401c5b027418d57cd117e5fe","source":{"kind":"arxiv","id":"1905.00741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00741","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00741v2","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00741","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZYOEDSTBXFTG","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZYOEDSTBXFTGHY4C","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZYOEDSTB","created_at":"2026-07-05T00:49:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZYOEDSTBXFTGHY4CG66F2ANAKP","target":"record","payload":{"canonical_record":{"source":{"id":"1905.00741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T13:42:51Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fc0e1b10b85501b455cb361fa1cd93db9fc246e86ad864d46e4ba0f793612ce0","abstract_canon_sha256":"dd7d687b36e4548a5a00389ffff5ed3ec549b599248123d76ef1690b1022a0db"},"schema_version":"1.0"},"canonical_sha256":"ce1c41ca61b96663e38237bc5d01a053c6dee447401c5b027418d57cd117e5fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:36.149670Z","signature_b64":"aiNnR/gwUG1qqCrJ9wSAeMgC6LUv/vq08NZeO0XmDgx7YXT41iqvB6oaZ6Ep1On1jj5fkjho84f2HWbTcb7aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce1c41ca61b96663e38237bc5d01a053c6dee447401c5b027418d57cd117e5fe","last_reissued_at":"2026-07-05T00:49:36.149179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:36.149179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.00741","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:49:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7l1g1FHftMeMgZYxsTyIYug6clBmRH+sHbmRL2EHPXFIC9ghoDURfTfDbxsizbBLutJV6YyMq6UDfzRZHHNHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:16:47.738425Z"},"content_sha256":"5827d1873d2c2033233691d92564f05cfe5a56545ae2f31449eafd88a1bdec85","schema_version":"1.0","event_id":"sha256:5827d1873d2c2033233691d92564f05cfe5a56545ae2f31449eafd88a1bdec85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZYOEDSTBXFTGHY4CG66F2ANAKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Video Game to Real Robot: The Transfer between Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anssi Kanervisto, Janne Karttunen, Ville Hautam\\\"aki, Ville Kyrki","submitted_at":"2019-05-02T13:42:51Z","abstract_excerpt":"Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training. To address this, transfer learning can be used to train the policy first in a simulated environment and then transfer it to physical agent. As the simulation never matches reality perfectly, the physics, visuals and action spaces by necessity differ between these environments to some degree. In this work, we study how general video games can be directly used instead of fine-tune"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00741","kind":"arxiv","version":2},"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/1905.00741/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":"2026-07-05T00:49:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B0VAL6bQjBaRvj8uWw/7zTUsLWu9bpxVXJOet7IIzCaLcf8QDbogDcIGgs/rL11SLNUxPXGFgdjjji3rJZ4mCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:16:47.739292Z"},"content_sha256":"e596b5b95e15313a2367ba07d80733fc4181478d6d751389d840827c2380c904","schema_version":"1.0","event_id":"sha256:e596b5b95e15313a2367ba07d80733fc4181478d6d751389d840827c2380c904"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/bundle.json","state_url":"https://pith.science/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/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":"2026-08-04T09:16:47Z","links":{"resolver":"https://pith.science/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP","bundle":"https://pith.science/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/bundle.json","state":"https://pith.science/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYOEDSTBXFTGHY4CG66F2ANAKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZYOEDSTBXFTGHY4CG66F2ANAKP","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":"dd7d687b36e4548a5a00389ffff5ed3ec549b599248123d76ef1690b1022a0db","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T13:42:51Z","title_canon_sha256":"fc0e1b10b85501b455cb361fa1cd93db9fc246e86ad864d46e4ba0f793612ce0"},"schema_version":"1.0","source":{"id":"1905.00741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00741","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00741v2","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00741","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZYOEDSTBXFTG","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZYOEDSTBXFTGHY4C","created_at":"2026-07-05T00:49:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZYOEDSTB","created_at":"2026-07-05T00:49:36Z"}],"graph_snapshots":[{"event_id":"sha256:e596b5b95e15313a2367ba07d80733fc4181478d6d751389d840827c2380c904","target":"graph","created_at":"2026-07-05T00:49:36Z","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/1905.00741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training. To address this, transfer learning can be used to train the policy first in a simulated environment and then transfer it to physical agent. As the simulation never matches reality perfectly, the physics, visuals and action spaces by necessity differ between these environments to some degree. In this work, we study how general video games can be directly used instead of fine-tune","authors_text":"Anssi Kanervisto, Janne Karttunen, Ville Hautam\\\"aki, Ville Kyrki","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T13:42:51Z","title":"From Video Game to Real Robot: The Transfer between Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00741","kind":"arxiv","version":2},"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":"sha256:5827d1873d2c2033233691d92564f05cfe5a56545ae2f31449eafd88a1bdec85","target":"record","created_at":"2026-07-05T00:49:36Z","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":"dd7d687b36e4548a5a00389ffff5ed3ec549b599248123d76ef1690b1022a0db","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-02T13:42:51Z","title_canon_sha256":"fc0e1b10b85501b455cb361fa1cd93db9fc246e86ad864d46e4ba0f793612ce0"},"schema_version":"1.0","source":{"id":"1905.00741","kind":"arxiv","version":2}},"canonical_sha256":"ce1c41ca61b96663e38237bc5d01a053c6dee447401c5b027418d57cd117e5fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce1c41ca61b96663e38237bc5d01a053c6dee447401c5b027418d57cd117e5fe","first_computed_at":"2026-07-05T00:49:36.149179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:36.149179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aiNnR/gwUG1qqCrJ9wSAeMgC6LUv/vq08NZeO0XmDgx7YXT41iqvB6oaZ6Ep1On1jj5fkjho84f2HWbTcb7aBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:36.149670Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5827d1873d2c2033233691d92564f05cfe5a56545ae2f31449eafd88a1bdec85","sha256:e596b5b95e15313a2367ba07d80733fc4181478d6d751389d840827c2380c904"],"state_sha256":"e2825fd4f0ee3c61f6898236c48d42d0ee3f3130b80e64dad82bee3a3114d134"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"awcR9ix3s4xeXfYtFdBoEtI1KBTIuAmGhfILBizu2gFZcY9NaS9EgTj/P7SZkpkj1ibVI0Wym5I4n96QpApYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:16:47.748680Z","bundle_sha256":"168d0251962c46bd0d4870232215bbf2d0213855d1537625fe75a2b80c994486"}}