{"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/efficientzero-v2-mastering-discrete-and","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","arxiv_id":"2403.00564","date":"2024-03-01","proceeding":null,"authors":["Shengjie Wang","Shaohuai Liu","Weirui Ye","Jiacheng You","Yang Gao"],"abstract":"Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior performance across diverse domains. In this paper, we introduce EfficientZero V2, a general framework designed for sample-efficient RL algorithms. We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs. With a series of improvements we propose, EfficientZero V2 outperforms the current state-of-the-art (SOTA) by a significant margin in diverse tasks under the limited data setting. EfficientZero V2 exhibits a notable advancement over the prevailing general algorithm, DreamerV3, achieving superior outcomes in 50 of 66 evaluated tasks across diverse benchmarks, such as Atari 100k, Proprio Control, and Vision Control.","url_abs":"https://arxiv.org/abs/2403.00564v2","url_pdf":"https://arxiv.org/pdf/2403.00564v2.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":"efficientzero-v2-mastering-discrete-and","repo_url":"https://github.com/shengjiewang-jason/efficientzerov2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.00564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00564"}},"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/shengjiewang-jason/efficientzerov2","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_draft_wrong":1,"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"18fbe72ffac82ee3","entry":"conv3x3","repo":"shengjiewang-jason/efficientzerov2","repo_kind":"official","path":"ez/agents/models/layer.py","file_url":"https://github.com/shengjiewang-jason/efficientzerov2/blob/HEAD/ez/agents/models/layer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"18fbe72ffac82ee3"}},{"code_sha256_prefix":"fac29a1ee33cbd15","entry":"cosine_similarity_loss","repo":"shengjiewang-jason/efficientzerov2","repo_kind":"official","path":"ez/utils/loss.py","file_url":"https://github.com/shengjiewang-jason/efficientzerov2/blob/HEAD/ez/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fac29a1ee33cbd15"}},{"code_sha256_prefix":"3d920a2bfcc14500","entry":"kl_loss","repo":"shengjiewang-jason/efficientzerov2","repo_kind":"official","path":"ez/utils/loss.py","file_url":"https://github.com/shengjiewang-jason/efficientzerov2/blob/HEAD/ez/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3d920a2bfcc14500"}},{"code_sha256_prefix":"1fcac51bd776abb0","entry":"mlp","repo":"shengjiewang-jason/efficientzerov2","repo_kind":"official","path":"ez/agents/models/layer.py","file_url":"https://github.com/shengjiewang-jason/efficientzerov2/blob/HEAD/ez/agents/models/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1fcac51bd776abb0"}},{"code_sha256_prefix":"0e1ecb268d4d4f47","entry":"train_ddp","repo":"shengjiewang-jason/efficientzerov2","repo_kind":"official","path":"ez/agents/base.py","file_url":"https://github.com/shengjiewang-jason/efficientzerov2/blob/HEAD/ez/agents/base.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0e1ecb268d4d4f47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}