{"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/premier-taco-pretraining-multitask","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","arxiv_id":"2402.06187","date":"2024-02-09","proceeding":null,"authors":["Ruijie Zheng","Yongyuan Liang","Xiyao Wang","Shuang Ma","Hal Daumé III","Huazhe Xu","John Langford","Praveen Palanisamy","Kalyan Shankar Basu","Furong Huang"],"abstract":"We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a general feature representation, which captures critical environmental dynamics and is fine-tuned using minimal expert demonstrations. It advances the temporal action contrastive learning (TACO) objective, known for state-of-the-art results in visual control tasks, by incorporating a novel negative example sampling strategy. This strategy is crucial in significantly boosting TACO's computational efficiency, making large-scale multitask offline pretraining feasible. Our extensive empirical evaluation in a diverse set of continuous control benchmarks including Deepmind Control Suite, MetaWorld, and LIBERO demonstrate Premier-TACO's effectiveness in pretraining visual representations, significantly enhancing few-shot imitation learning of novel tasks. Our code, pretraining data, as well as pretrained model checkpoints will be released at https://github.com/PremierTACO/premier-taco. Our project webpage is at https://premiertaco.github.io.","url_abs":"https://arxiv.org/abs/2402.06187v4","url_pdf":"https://arxiv.org/pdf/2402.06187v4.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":"premier-taco-pretraining-multitask","repo_url":"https://github.com/premiertaco/premier-taco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"few-shot-imitation-learning","task_name":"Few-Shot Imitation Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.06187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06187"}},"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":"deterministic:regex_extraction","url":"https://github.com/PremierTACO/premier-taco","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/premiertaco/premier-taco","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":8,"samples":[{"code_sha256_prefix":"93768277f8d3a9c3","entry":"choose","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"replay_buffer.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/replay_buffer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93768277f8d3a9c3"}},{"code_sha256_prefix":"9f840a22d31a89bc","entry":"episode_len","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"replay_buffer.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/replay_buffer.py","link_basis":"harvester_set","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":"9f840a22d31a89bc"}},{"code_sha256_prefix":"f55fa75eaa288304","entry":"expectile_loss","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"utils.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f55fa75eaa288304"}},{"code_sha256_prefix":"284dd761a9579d78","entry":"load_episode","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"replay_buffer.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/replay_buffer.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":"284dd761a9579d78"}},{"code_sha256_prefix":"6244e9922f4e0610","entry":"to_torch","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"utils.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/utils.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6244e9922f4e0610"}},{"code_sha256_prefix":"b0eabbe4f3ba312b","entry":"to_torch_distribute","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"utils.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/utils.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":"b0eabbe4f3ba312b"}},{"code_sha256_prefix":"f1ba293af9a573fd","entry":"make_agent","repo":"PremierTACO/premier-taco","repo_kind":"official","path":"train_bc.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/train_bc.py","link_basis":"plan_row","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":"f1ba293af9a573fd"}},{"code_sha256_prefix":"ff56a87a6c0c857f","entry":"make_agent","repo":"premiertaco/premier-taco","repo_kind":"official","path":"train_premier_taco_dist.py","file_url":"https://github.com/premiertaco/premier-taco/blob/HEAD/train_premier_taco_dist.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":"ff56a87a6c0c857f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}