{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EOOXEKK223KIV2MB35VCMTW3QB","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":"cbf5780ad9407da84ca65515509f84b2b6f5365e82ab195441f744cc53d3818f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-17T17:25:52Z","title_canon_sha256":"04baf7bb9e1c7de491339a75f20c2cec137f864ee58a7f789c2c4e30cbe9ca2f"},"schema_version":"1.0","source":{"id":"2004.08356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08356","created_at":"2026-07-05T00:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08356v1","created_at":"2026-07-05T00:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08356","created_at":"2026-07-05T00:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"EOOXEKK223KI","created_at":"2026-07-05T00:55:52Z"},{"alias_kind":"pith_short_16","alias_value":"EOOXEKK223KIV2MB","created_at":"2026-07-05T00:55:52Z"},{"alias_kind":"pith_short_8","alias_value":"EOOXEKK2","created_at":"2026-07-05T00:55:52Z"}],"graph_snapshots":[{"event_id":"sha256:68f02207626d3bf49f6a8f3385838b1bfb41b792b112767344106ad8b2a02455","target":"graph","created_at":"2026-07-05T00:55:52Z","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/2004.08356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel approach to learn goal-conditioned policies for locomotion in a batch RL setting. The batch data is collected by a policy that is not goal-conditioned. For the locomotion task, this translates to data collection using a policy learnt by the agent for walking straight in one direction, and using that data to learn a goal-conditioned policy that enables the agent to walk in any direction. The data collection policy used should be invariant to the direction the agent is facing i.e. regardless of its initial orientation, the agent should take the same actions to walk forward. We","authors_text":"Aditi Mavalankar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-17T17:25:52Z","title":"Goal-conditioned Batch Reinforcement Learning for Rotation Invariant Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08356","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":"sha256:91ef48c2a5f8149ccd17219deed5216d8b58fe7a201f2aab328accee36a5a520","target":"record","created_at":"2026-07-05T00:55:52Z","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":"cbf5780ad9407da84ca65515509f84b2b6f5365e82ab195441f744cc53d3818f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-17T17:25:52Z","title_canon_sha256":"04baf7bb9e1c7de491339a75f20c2cec137f864ee58a7f789c2c4e30cbe9ca2f"},"schema_version":"1.0","source":{"id":"2004.08356","kind":"arxiv","version":1}},"canonical_sha256":"239d72295ad6d48ae981df6a264edb806442e656cd65a7f37f0d51005a6f4749","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"239d72295ad6d48ae981df6a264edb806442e656cd65a7f37f0d51005a6f4749","first_computed_at":"2026-07-05T00:55:52.496489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:52.496489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6ZM1q7EmxDRP95rC2F9T5kPmQUBr+IYIUPo6LviwNaP8MwVyt5B8ZTmI8iFuXOraahxvSsJNgx/vFNs+JwkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:52.496968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.08356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91ef48c2a5f8149ccd17219deed5216d8b58fe7a201f2aab328accee36a5a520","sha256:68f02207626d3bf49f6a8f3385838b1bfb41b792b112767344106ad8b2a02455"],"state_sha256":"ebf4575de34d70009ef766c4b67413949d46692ffb5ae9d22feccaab73dd1941"}