{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RDJT4NEUP6FWWMPZ7SW4L2X2MO","short_pith_number":"pith:RDJT4NEU","canonical_record":{"source":{"id":"1709.08430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-25T11:29:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f3d459f7381a72def184f8791e6779aa74f06910b07fdeb1e45ea0768262cc67","abstract_canon_sha256":"1e4619c942eab011588c953c103c05a90fcab11e380e6bd798b860e75b16140f"},"schema_version":"1.0"},"canonical_sha256":"88d33e34947f8b6b31f9fcadc5eafa6399460d5855eb66437cf0cd5612263071","source":{"kind":"arxiv","id":"1709.08430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08430","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08430v1","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08430","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"pith_short_12","alias_value":"RDJT4NEUP6FW","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDJT4NEUP6FWWMPZ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDJT4NEU","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RDJT4NEUP6FWWMPZ7SW4L2X2MO","target":"record","payload":{"canonical_record":{"source":{"id":"1709.08430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-25T11:29:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f3d459f7381a72def184f8791e6779aa74f06910b07fdeb1e45ea0768262cc67","abstract_canon_sha256":"1e4619c942eab011588c953c103c05a90fcab11e380e6bd798b860e75b16140f"},"schema_version":"1.0"},"canonical_sha256":"88d33e34947f8b6b31f9fcadc5eafa6399460d5855eb66437cf0cd5612263071","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:25.681529Z","signature_b64":"RspezyWAMaJhchB/3N3WgeEOWecfNJRy2EJNUbHKkuPNQOEMb8bk+tye0QyTdHpeY2uzC12ywBLocJsuJTj1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d33e34947f8b6b31f9fcadc5eafa6399460d5855eb66437cf0cd5612263071","last_reissued_at":"2026-05-18T00:34:25.681083Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:25.681083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.08430","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":"2026-05-18T00:34:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMDGqKKkoImJIV3d6zKvB9Hais929NxHJ8FR8Dl2I8daV5hAgY5V6rGnkJwgivkeWtHBSapPKgE7gRrQKa5bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:08:54.627437Z"},"content_sha256":"7c5ac68364cfdb07969a50e2e0020fa876dc51f1d0a015e7aa69feef5b501a17","schema_version":"1.0","event_id":"sha256:7c5ac68364cfdb07969a50e2e0020fa876dc51f1d0a015e7aa69feef5b501a17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RDJT4NEUP6FWWMPZ7SW4L2X2MO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Giuseppe Paolo, Lei Tai, Ming Liu","submitted_at":"2017-09-25T11:29:34Z","abstract_excerpt":"In this paper we focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach. The work is based on the deep deterministic policy gradient (DDPG) algorithm, proven to be very successful in simple simulation environments. The algorithm works in an end-to-end fashion in order to control the continuous position of the flippers. This end-to-end approach makes it easy to apply the controller to a wide array of circumstances, but the huge flexibility comes to the cost of an increased difficulty of solution. The complexity of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08430","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":"2026-05-18T00:34:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XSrs67tBZPYEsWkiiR66tcG6SdecwqGiuEMrnmpsUxxYorGS0sKUUh9xF8utCFvaYOnJaePW3tuEQsZHk1SsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:08:54.628097Z"},"content_sha256":"4bb89c0b3872ab4989984cb3e84b44e077c6720a8b23458709fca900f0a6ae7e","schema_version":"1.0","event_id":"sha256:4bb89c0b3872ab4989984cb3e84b44e077c6720a8b23458709fca900f0a6ae7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/bundle.json","state_url":"https://pith.science/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/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":"2026-05-25T23:08:54Z","links":{"resolver":"https://pith.science/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO","bundle":"https://pith.science/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/bundle.json","state":"https://pith.science/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDJT4NEUP6FWWMPZ7SW4L2X2MO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RDJT4NEUP6FWWMPZ7SW4L2X2MO","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":"1e4619c942eab011588c953c103c05a90fcab11e380e6bd798b860e75b16140f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-25T11:29:34Z","title_canon_sha256":"f3d459f7381a72def184f8791e6779aa74f06910b07fdeb1e45ea0768262cc67"},"schema_version":"1.0","source":{"id":"1709.08430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08430","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08430v1","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08430","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"pith_short_12","alias_value":"RDJT4NEUP6FW","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDJT4NEUP6FWWMPZ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDJT4NEU","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:4bb89c0b3872ab4989984cb3e84b44e077c6720a8b23458709fca900f0a6ae7e","target":"graph","created_at":"2026-05-18T00:34:25Z","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 focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach. The work is based on the deep deterministic policy gradient (DDPG) algorithm, proven to be very successful in simple simulation environments. The algorithm works in an end-to-end fashion in order to control the continuous position of the flippers. This end-to-end approach makes it easy to apply the controller to a wide array of circumstances, but the huge flexibility comes to the cost of an increased difficulty of solution. The complexity of the ","authors_text":"Giuseppe Paolo, Lei Tai, Ming Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-25T11:29:34Z","title":"Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08430","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":"sha256:7c5ac68364cfdb07969a50e2e0020fa876dc51f1d0a015e7aa69feef5b501a17","target":"record","created_at":"2026-05-18T00:34:25Z","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":"1e4619c942eab011588c953c103c05a90fcab11e380e6bd798b860e75b16140f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-25T11:29:34Z","title_canon_sha256":"f3d459f7381a72def184f8791e6779aa74f06910b07fdeb1e45ea0768262cc67"},"schema_version":"1.0","source":{"id":"1709.08430","kind":"arxiv","version":1}},"canonical_sha256":"88d33e34947f8b6b31f9fcadc5eafa6399460d5855eb66437cf0cd5612263071","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88d33e34947f8b6b31f9fcadc5eafa6399460d5855eb66437cf0cd5612263071","first_computed_at":"2026-05-18T00:34:25.681083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:25.681083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RspezyWAMaJhchB/3N3WgeEOWecfNJRy2EJNUbHKkuPNQOEMb8bk+tye0QyTdHpeY2uzC12ywBLocJsuJTj1DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:25.681529Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.08430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c5ac68364cfdb07969a50e2e0020fa876dc51f1d0a015e7aa69feef5b501a17","sha256:4bb89c0b3872ab4989984cb3e84b44e077c6720a8b23458709fca900f0a6ae7e"],"state_sha256":"47ae073c017c29b004e48626fa559da1f43810826d9c6688bf76472719ad348d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmUYaJ6P3e43P4mgnLH3CYgz888AqMvKK9K1HVKkWX7Dz/DG2NZqTPVf1MYjj45qBNpc5S/RrCY+n9zRcYxRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:08:54.631426Z","bundle_sha256":"59159a86013c925a8d9f2ef8f0bfbeb1dab0bd0606cd80b7508563704e7cb831"}}