{"work":{"id":"360ec5fb-79fd-4490-bc73-3d161609c42d","openalex_id":null,"doi":null,"arxiv_id":"2310.16828","raw_key":null,"title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","authors":null,"authors_text":"Nicklas Hansen, Hao Su, Xiaolong Wang","year":2023,"venue":"cs.LG","abstract":"TD-MPC is a model-based reinforcement learning (RL) algorithm that performs local trajectory optimization in the latent space of a learned implicit (decoder-free) world model. In this work, we present TD-MPC2: a series of improvements upon the TD-MPC algorithm. We demonstrate that TD-MPC2 improves significantly over baselines across 104 online RL tasks spanning 4 diverse task domains, achieving consistently strong results with a single set of hyperparameters. We further show that agent capabilities increase with model and data size, and successfully train a single 317M parameter agent to perform 80 tasks across multiple task domains, embodiments, and action spaces. We conclude with an account of lessons, opportunities, and risks associated with large TD-MPC2 agents. Explore videos, models, data, code, and more at https://tdmpc2.com","external_url":"https://arxiv.org/abs/2310.16828","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T07:50:29.260924+00:00","pith_arxiv_id":"2310.16828","created_at":"2026-05-10T00:59:49.488793+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","render_title":"TD-MPC2: Scalable, Robust World Models for Continuous Control"},"hub":{"state":{"work_id":"360ec5fb-79fd-4490-bc73-3d161609c42d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":36,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2023-10-04T07:56:42+00:00","last_pith_cited_at":"2026-05-20T22:58:15+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-08T18:33:52.489963+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":10},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":10},{"context_polarity":"baseline","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}