Research map / Optimization / Distributed and compressed
Distributed Multitask Reinforcement Learning with Quadratic Convergence
Rasul Tutunov, Dongho Kim, Haitham Bou Ammar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use distributed SDD-Newton instead of ADD, ADMM, distributed averaging, Network Newton and sub-gradients | Distributed multitask RL solver · SM, DM, CP, HC, HR systems, random graph of 20 nodes and 50 edges | time to convergence (10^-5 error threshold) | Improved |
| use distributed SDD-Newton instead of other distributed methods on different graph topologies | Distributed multitask RL solver · HC with small, medium, large random graphs and bar-bell graph | iterations to 10^-5 consensus error | Improved |
| tighten accuracy requirement, with SDD-Newton communication growing with graph condition number | Distributed SDD-Newton · HC system | local communication exchange | Improved |
| use SDD-Newton instead of PG-ELLA, GO-MTL and Dist-ADMM | Multitask RL · SM, CP, HC, DM | jump-start improvement % | Improved |
| use SDD-Newton instead of streaming models such as PG-ELLA | Multitask RL · SM, CP, HC, DM | asymptotic performance % | Improved |
Closest papers by meaning
- Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer (ICML 2025 · similarity 0.88)
- Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks (ICLR 2024 · similarity 0.88)
- Representation Learning Enables Scalable Multitask Deep Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds (NeurIPS 2025 · similarity 0.87)
- AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers (NeurIPS 2024 · similarity 0.87)
- Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
