{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EPJ4NDVOZAE5STZWIZ3LK36BY3","short_pith_number":"pith:EPJ4NDVO","canonical_record":{"source":{"id":"1802.10463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T10:26:08Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"ec3bce5a6fd2ac2808d286eb2c54a65de6c59debfceec731f23bbee4cd68d210","abstract_canon_sha256":"5a49ecfc5d9b47f2ff94af2a5e23b5299a7a26bfab993e108e7705352f712be8"},"schema_version":"1.0"},"canonical_sha256":"23d3c68eaec809d94f364676b56fc1c6dbf2cc462187ca2b30feef5bb5d604af","source":{"kind":"arxiv","id":"1802.10463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10463","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10463v1","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10463","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"EPJ4NDVOZAE5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPJ4NDVOZAE5STZW","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPJ4NDVO","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EPJ4NDVOZAE5STZWIZ3LK36BY3","target":"record","payload":{"canonical_record":{"source":{"id":"1802.10463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T10:26:08Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"ec3bce5a6fd2ac2808d286eb2c54a65de6c59debfceec731f23bbee4cd68d210","abstract_canon_sha256":"5a49ecfc5d9b47f2ff94af2a5e23b5299a7a26bfab993e108e7705352f712be8"},"schema_version":"1.0"},"canonical_sha256":"23d3c68eaec809d94f364676b56fc1c6dbf2cc462187ca2b30feef5bb5d604af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:17.077519Z","signature_b64":"wQuw4LD86ISP+k7fbiiTpNvhnS1HXnGDAS+DO/Wu04tbBTm9OU89Xk+9G5tYD82Dap1QPcIVjXIn+ksQYGIzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d3c68eaec809d94f364676b56fc1c6dbf2cc462187ca2b30feef5bb5d604af","last_reissued_at":"2026-05-18T00:22:17.076929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:17.076929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.10463","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":"2026-05-18T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uz357Ev21uRgfLRSH5ET0B0Hp+wBsu/FXAGA8+UnxJY9rOvkkP7Lq6w6MCK0PXExk5lPNOcr83JSdLUBkTvLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:10:41.255407Z"},"content_sha256":"cbecb627087b9e5c71c941ca75de924b2a4145f799c4c3344aeb227405fc8d7a","schema_version":"1.0","event_id":"sha256:cbecb627087b9e5c71c941ca75de924b2a4145f799c4c3344aeb227405fc8d7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EPJ4NDVOZAE5STZWIZ3LK36BY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiGrad: Multi-Task Reinforcement Learning with Shared Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Sarkar, Balaraman Ravindran, K Madhava Krishna, Parijat Dewangan, S Phaniteja","submitted_at":"2018-02-27T10:26:08Z","abstract_excerpt":"Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound policy may get biased towards a task or the gradients from different tasks negate each other, making the learning unstable and sometimes less data efficient. In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10463","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":"2026-05-18T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmZVh2ZxYfVICvaq2LY2YlBZVmp5KhEMUM6LQ6g9DVyZ4AavczJvz7EtP2KDFqmv12pP4i/hmZxpiGogt+SRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:10:41.256116Z"},"content_sha256":"cd61d62515dd05a993841dbfe77690748f1797ec7e7dceb6ccced89dc77c2757","schema_version":"1.0","event_id":"sha256:cd61d62515dd05a993841dbfe77690748f1797ec7e7dceb6ccced89dc77c2757"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/bundle.json","state_url":"https://pith.science/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/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":"2026-05-27T07:10:41Z","links":{"resolver":"https://pith.science/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3","bundle":"https://pith.science/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/bundle.json","state":"https://pith.science/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPJ4NDVOZAE5STZWIZ3LK36BY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EPJ4NDVOZAE5STZWIZ3LK36BY3","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":"5a49ecfc5d9b47f2ff94af2a5e23b5299a7a26bfab993e108e7705352f712be8","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T10:26:08Z","title_canon_sha256":"ec3bce5a6fd2ac2808d286eb2c54a65de6c59debfceec731f23bbee4cd68d210"},"schema_version":"1.0","source":{"id":"1802.10463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10463","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10463v1","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10463","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"EPJ4NDVOZAE5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPJ4NDVOZAE5STZW","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPJ4NDVO","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:cd61d62515dd05a993841dbfe77690748f1797ec7e7dceb6ccced89dc77c2757","target":"graph","created_at":"2026-05-18T00:22:17Z","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":"Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound policy may get biased towards a task or the gradients from different tasks negate each other, making the learning unstable and sometimes less data efficient. In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continu","authors_text":"Abhishek Sarkar, Balaraman Ravindran, K Madhava Krishna, Parijat Dewangan, S Phaniteja","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T10:26:08Z","title":"DiGrad: Multi-Task Reinforcement Learning with Shared Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10463","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:cbecb627087b9e5c71c941ca75de924b2a4145f799c4c3344aeb227405fc8d7a","target":"record","created_at":"2026-05-18T00:22:17Z","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":"5a49ecfc5d9b47f2ff94af2a5e23b5299a7a26bfab993e108e7705352f712be8","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T10:26:08Z","title_canon_sha256":"ec3bce5a6fd2ac2808d286eb2c54a65de6c59debfceec731f23bbee4cd68d210"},"schema_version":"1.0","source":{"id":"1802.10463","kind":"arxiv","version":1}},"canonical_sha256":"23d3c68eaec809d94f364676b56fc1c6dbf2cc462187ca2b30feef5bb5d604af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23d3c68eaec809d94f364676b56fc1c6dbf2cc462187ca2b30feef5bb5d604af","first_computed_at":"2026-05-18T00:22:17.076929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:17.076929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQuw4LD86ISP+k7fbiiTpNvhnS1HXnGDAS+DO/Wu04tbBTm9OU89Xk+9G5tYD82Dap1QPcIVjXIn+ksQYGIzBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:17.077519Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbecb627087b9e5c71c941ca75de924b2a4145f799c4c3344aeb227405fc8d7a","sha256:cd61d62515dd05a993841dbfe77690748f1797ec7e7dceb6ccced89dc77c2757"],"state_sha256":"14882a712e6fad51473ee4bc756da986e8ae15ac19ab70358de44cd9f40e99ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dSW3YM1rAAAzD2jMSVqf79cEBsUJ9D2ZXGSljZFNMt0baulmRbT4YoaiHejJ9HMG5hSlvIkAVVE5y3OKYB+xDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:10:41.260545Z","bundle_sha256":"1fb169a40c57fd38feb7904b89457ec815fa31b51f2ca9be1917f8d435cca63f"}}