{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/anti-exploration-by-random-network","title":"Anti-Exploration by Random Network Distillation","arxiv_id":"2301.13616","date":"2023-01-31","proceeding":null,"authors":["Alexander Nikulin","Vladislav Kurenkov","Denis Tarasov","Sergey Kolesnikov"],"abstract":"Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-distribution actions in offline reinforcement learning. In this paper, we revisit these results and show that, with a naive choice of conditioning for the RND prior, it becomes infeasible for the actor to effectively minimize the anti-exploration bonus and discriminativity is not an issue. We show that this limitation can be avoided with conditioning based on Feature-wise Linear Modulation (FiLM), resulting in a simple and efficient ensemble-free algorithm based on Soft Actor-Critic. We evaluate it on the D4RL benchmark, showing that it is capable of achieving performance comparable to ensemble-based methods and outperforming ensemble-free approaches by a wide margin.","url_abs":"https://arxiv.org/abs/2301.13616v2","url_pdf":"https://arxiv.org/pdf/2301.13616v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"anti-exploration-by-random-network","repo_url":"https://github.com/tinkoff-ai/sac-rnd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"anti-exploration-by-random-network","repo_url":"https://github.com/zzmtsvv/sac_drnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"anti-exploration-by-random-network","repo_url":"https://github.com/zzmtsvv/sac_rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.13616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13616"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzmtsvv/sac_rnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzmtsvv/sac_drnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tinkoff-ai/sac-rnd","reach":null}],"summary":{"ran":18,"ran_honours":1,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":18,"ran":17,"repositories":1},"listed":{"samples":7,"ran":3,"repositories":2},"community":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"d69bcc085240a24a","entry":"BilinearDense","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d69bcc085240a24a"}},{"code_sha256_prefix":"8f6f4cff35de62cf","entry":"BilinearFirstMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f6f4cff35de62cf"}},{"code_sha256_prefix":"0f917b109efda65c","entry":"BilinearFullMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f917b109efda65c"}},{"code_sha256_prefix":"a231dfdd79465ac6","entry":"BilinearLastMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a231dfdd79465ac6"}},{"code_sha256_prefix":"bd41551ec9638504","entry":"ConcatFirstMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd41551ec9638504"}},{"code_sha256_prefix":"41028f940725e4a0","entry":"ConcatFullMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41028f940725e4a0"}},{"code_sha256_prefix":"21b612feebc3499d","entry":"ConcatLastMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21b612feebc3499d"}},{"code_sha256_prefix":"ceefac1ae561a6c3","entry":"FiLM","repo":"zzmtsvv/sac_rnd","repo_kind":"listed","path":"rnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_rnd/blob/HEAD/rnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ceefac1ae561a6c3"}},{"code_sha256_prefix":"be3f4b3f06b0e6bd","entry":"FilmFirstMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be3f4b3f06b0e6bd"}},{"code_sha256_prefix":"91e0406ad5665e10","entry":"FilmFullMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91e0406ad5665e10"}},{"code_sha256_prefix":"3ea09b9fb948e867","entry":"FilmLastMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ea09b9fb948e867"}},{"code_sha256_prefix":"12f4f05b82493956","entry":"GatedMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12f4f05b82493956"}},{"code_sha256_prefix":"590f9905be494072","entry":"PredictorNetwork","repo":"zzmtsvv/sac_rnd","repo_kind":"listed","path":"rnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_rnd/blob/HEAD/rnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"590f9905be494072"}},{"code_sha256_prefix":"d33f9e805bac2d2e","entry":"PriorNetwork","repo":"zzmtsvv/sac_rnd","repo_kind":"listed","path":"rnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_rnd/blob/HEAD/rnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d33f9e805bac2d2e"}},{"code_sha256_prefix":"f08bbf7286cf9812","entry":"TorchBilinearDense","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f08bbf7286cf9812"}},{"code_sha256_prefix":"7131c9d471efe1a4","entry":"TorchBilinearFirstMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7131c9d471efe1a4"}},{"code_sha256_prefix":"93814161ebae72e3","entry":"TorchBilinearFullMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93814161ebae72e3"}},{"code_sha256_prefix":"a9a4771d15f5a324","entry":"TorchBilinearLastMLP","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9a4771d15f5a324"}},{"code_sha256_prefix":"adb37ed22c2703a9","entry":"normalize","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"adb37ed22c2703a9"}},{"code_sha256_prefix":"b62cf8b42971d060","entry":"pytorch_init","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b62cf8b42971d060"}},{"code_sha256_prefix":"c901b83a37fd3070","entry":"DRND","repo":"zzmtsvv/sac_drnd","repo_kind":"listed","path":"drnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_drnd/blob/HEAD/drnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c901b83a37fd3070"}},{"code_sha256_prefix":"7120bed03164d5ad","entry":"EnsembledFiLM","repo":"zzmtsvv/sac_drnd","repo_kind":"listed","path":"drnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_drnd/blob/HEAD/drnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7120bed03164d5ad"}},{"code_sha256_prefix":"bc04133ae453cf88","entry":"EnsembledTargetNetwork","repo":"zzmtsvv/sac_drnd","repo_kind":"listed","path":"drnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_drnd/blob/HEAD/drnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc04133ae453cf88"}},{"code_sha256_prefix":"ffdc71693d91c600","entry":"RND","repo":"tinkoff-ai/sac-rnd","repo_kind":"official","path":"offline_sac/networks.py","file_url":"https://github.com/tinkoff-ai/sac-rnd/blob/HEAD/offline_sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffdc71693d91c600"}},{"code_sha256_prefix":"28ed96e0bf8e9eab","entry":"RND","repo":"zzmtsvv/sac_rnd","repo_kind":"listed","path":"rnd_modules.py","file_url":"https://github.com/zzmtsvv/sac_rnd/blob/HEAD/rnd_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28ed96e0bf8e9eab"}},{"code_sha256_prefix":"226a9594f55e107f","entry":"train","repo":"shidilrzf/anti-exploration-rl","repo_kind":"community","path":"examples/train_ae.py","file_url":"https://github.com/shidilrzf/anti-exploration-rl/blob/HEAD/examples/train_ae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"226a9594f55e107f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}