{"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/meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","arxiv_id":"2410.11448","date":"2024-10-15","proceeding":null,"authors":["Zhi Wang","Li Zhang","Wenhao Wu","Yuanheng Zhu","Dongbin Zhao","Chunlin Chen"],"abstract":"A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision communities have seen remarkable progress toward this trend by scaling up transformer-based models trained on massive datasets, while reinforcement learning (RL) agents still suffer from poor generalization capacity under such paradigms. To tackle this challenge, we propose Meta Decision Transformer (Meta-DT), which leverages the sequential modeling ability of the transformer architecture and robust task representation learning via world model disentanglement to achieve efficient generalization in offline meta-RL. We pretrain a context-aware world model to learn a compact task representation, and inject it as a contextual condition to the causal transformer to guide task-oriented sequence generation. Then, we subtly utilize history trajectories generated by the meta-policy as a self-guided prompt to exploit the architectural inductive bias. We select the trajectory segment that yields the largest prediction error on the pretrained world model to construct the prompt, aiming to encode task-specific information complementary to the world model maximally. Notably, the proposed framework eliminates the requirement of any expert demonstration or domain knowledge at test time. Experimental results on MuJoCo and Meta-World benchmarks across various dataset types show that Meta-DT exhibits superior few and zero-shot generalization capacity compared to strong baselines while being more practical with fewer prerequisites. Our code is available at https://github.com/NJU-RL/Meta-DT.","url_abs":"https://arxiv.org/abs/2410.11448v2","url_pdf":"https://arxiv.org/pdf/2410.11448v2.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":"meta-dt-offline-meta-rl-as-conditional","repo_url":"https://github.com/nju-rl/meta-dt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.11448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11448"}},"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/NJU-RL/Meta-DT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nju-rl/meta-dt","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"0161b27cbe3cc58d","entry":"discount_cumsum","repo":"NJU-RL/Meta-DT","repo_kind":"official","path":"meta_dt/dataset.py","file_url":"https://github.com/NJU-RL/Meta-DT/blob/HEAD/meta_dt/dataset.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0161b27cbe3cc58d"}},{"code_sha256_prefix":"ef264ae3fc346aac","entry":"append_context_to_data","repo":"NJU-RL/Meta-DT","repo_kind":"official","path":"meta_dt/dataset.py","file_url":"https://github.com/NJU-RL/Meta-DT/blob/HEAD/meta_dt/dataset.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":"ef264ae3fc346aac"}},{"code_sha256_prefix":"304e02d6255a7b8d","entry":"append_error_to_trajectory","repo":"NJU-RL/Meta-DT","repo_kind":"official","path":"meta_dt/dataset.py","file_url":"https://github.com/NJU-RL/Meta-DT/blob/HEAD/meta_dt/dataset.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":"304e02d6255a7b8d"}},{"code_sha256_prefix":"00a33466c69c5705","entry":"load_tf_weights_in_gpt2","repo":"NJU-RL/Meta-DT","repo_kind":"official","path":"meta_dt/trajectory_gpt2.py","file_url":"https://github.com/NJU-RL/Meta-DT/blob/HEAD/meta_dt/trajectory_gpt2.py","link_basis":"harvester_set","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":"00a33466c69c5705"}},{"code_sha256_prefix":"2099fffc2b5e87af","entry":"meta_evaluate_episode_rtg","repo":"NJU-RL/Meta-DT","repo_kind":"official","path":"meta_dt/evaluation.py","file_url":"https://github.com/NJU-RL/Meta-DT/blob/HEAD/meta_dt/evaluation.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":"2099fffc2b5e87af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}