{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DV2GB2SDS6TGAENFDUSUI4ZUCY","short_pith_number":"pith:DV2GB2SD","canonical_record":{"source":{"id":"1702.08165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-27T07:16:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a56bd6d19392a5a576d600fe2dd87fdd8d70fb957a236a72781171e183a2564d","abstract_canon_sha256":"850219589e3c015b7b5a9359f19f36275fe231e3eab2a577757ddaa05530436e"},"schema_version":"1.0"},"canonical_sha256":"1d7460ea4397a66011a51d2544733416360a8cedf0e6cd94e9a78841dc715288","source":{"kind":"arxiv","id":"1702.08165","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08165","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08165v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08165","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"DV2GB2SDS6TG","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DV2GB2SDS6TGAENF","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DV2GB2SD","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DV2GB2SDS6TGAENFDUSUI4ZUCY","target":"record","payload":{"canonical_record":{"source":{"id":"1702.08165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-27T07:16:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a56bd6d19392a5a576d600fe2dd87fdd8d70fb957a236a72781171e183a2564d","abstract_canon_sha256":"850219589e3c015b7b5a9359f19f36275fe231e3eab2a577757ddaa05530436e"},"schema_version":"1.0"},"canonical_sha256":"1d7460ea4397a66011a51d2544733416360a8cedf0e6cd94e9a78841dc715288","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.786915Z","signature_b64":"eEnRqDn+f4ax2A0pFsYwKSWPUOqXW8ZpPUCWmgVvhkFCf+XYki550iMaGGxY+yV3gVjS3o4J9rIVJxiCEcZaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7460ea4397a66011a51d2544733416360a8cedf0e6cd94e9a78841dc715288","last_reissued_at":"2026-05-18T00:39:46.786245Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.786245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.08165","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYiUc4Y4GrKtHoOoDgSX/CGruK6fKtbKWmaL2X+2Y5t9h0BVye+pcSWPzr/t4xMeqPaS1DVMOgFJXbaUFQzaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:32:28.809827Z"},"content_sha256":"e917af31d3d892ee8f93abfbcdb4c8d3f784313acb54df7adb5e07e809737c69","schema_version":"1.0","event_id":"sha256:e917af31d3d892ee8f93abfbcdb4c8d3f784313acb54df7adb5e07e809737c69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DV2GB2SDS6TGAENFDUSUI4ZUCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Deep Energy-Based Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran Tang, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja","submitted_at":"2017-02-27T07:16:41Z","abstract_excerpt":"We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08165","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":""},"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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvoUm9eUHXnpBKH9xePZ/hUD2cfWPtkhRTNoH41El49N3fQx/lrjn5uOCfxTDtQu79GjisKSLUJwB1WXUUMDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:32:28.810173Z"},"content_sha256":"7f0fb88170d59ba5565c8d63ed3278363e10f6689ddc6381407ae2ad704f93a8","schema_version":"1.0","event_id":"sha256:7f0fb88170d59ba5565c8d63ed3278363e10f6689ddc6381407ae2ad704f93a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/bundle.json","state_url":"https://pith.science/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/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":"2026-05-30T05:32:28Z","links":{"resolver":"https://pith.science/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY","bundle":"https://pith.science/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/bundle.json","state":"https://pith.science/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DV2GB2SDS6TGAENFDUSUI4ZUCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DV2GB2SDS6TGAENFDUSUI4ZUCY","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":"850219589e3c015b7b5a9359f19f36275fe231e3eab2a577757ddaa05530436e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-27T07:16:41Z","title_canon_sha256":"a56bd6d19392a5a576d600fe2dd87fdd8d70fb957a236a72781171e183a2564d"},"schema_version":"1.0","source":{"id":"1702.08165","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08165","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08165v2","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08165","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"DV2GB2SDS6TG","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DV2GB2SDS6TGAENF","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DV2GB2SD","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:7f0fb88170d59ba5565c8d63ed3278363e10f6689ddc6381407ae2ad704f93a8","target":"graph","created_at":"2026-05-18T00:39:46Z","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":"We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows t","authors_text":"Haoran Tang, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-27T07:16:41Z","title":"Reinforcement Learning with Deep Energy-Based Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08165","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:e917af31d3d892ee8f93abfbcdb4c8d3f784313acb54df7adb5e07e809737c69","target":"record","created_at":"2026-05-18T00:39:46Z","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":"850219589e3c015b7b5a9359f19f36275fe231e3eab2a577757ddaa05530436e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-27T07:16:41Z","title_canon_sha256":"a56bd6d19392a5a576d600fe2dd87fdd8d70fb957a236a72781171e183a2564d"},"schema_version":"1.0","source":{"id":"1702.08165","kind":"arxiv","version":2}},"canonical_sha256":"1d7460ea4397a66011a51d2544733416360a8cedf0e6cd94e9a78841dc715288","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d7460ea4397a66011a51d2544733416360a8cedf0e6cd94e9a78841dc715288","first_computed_at":"2026-05-18T00:39:46.786245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:46.786245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eEnRqDn+f4ax2A0pFsYwKSWPUOqXW8ZpPUCWmgVvhkFCf+XYki550iMaGGxY+yV3gVjS3o4J9rIVJxiCEcZaCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:46.786915Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08165","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e917af31d3d892ee8f93abfbcdb4c8d3f784313acb54df7adb5e07e809737c69","sha256:7f0fb88170d59ba5565c8d63ed3278363e10f6689ddc6381407ae2ad704f93a8"],"state_sha256":"e92deaaeeca134b327deec64b4a47bebc307858c9dcfec6f9095de4cdc0670db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LrbtpLhtfQb9H+wCTqiMMAHzutiuKu066jWOJ0QPaG4URPNU+O4WfJYSBfRduYbfA1STtLg6C8ADOomY8wOYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:32:28.812136Z","bundle_sha256":"6fb4eb9e427b2f4b5bffd9c75a22085a25b632d55fe1bf7a34684b2138f3eaed"}}