Research map / Multi-agent systems and games / Cooperative multi-agent RL
Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
Xuefeng Wang, Lei Zhang, Henglin Pu, Ahmed H Qureshi, Husheng Li
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 |
|---|---|---|---|
| add the VGI value-gradient loss to VIP (ablation) | VIP · continuous-time MPE and multi-agent MuJoCo | mean cumulative reward | Improved |
| add VGI loss (ablation) | VIP · Coupled oscillator | absolute value-gradient error: above 0.08 -> below 0.02 | Improved |
| use Tanh instead of ReLU activation in the critic (ablation) | VIP · MuJoCo and MPE tasks | accumulated reward | Improved |
| balance all critic loss weights instead of up-weighting anchor or HJB residual (ablation) | VIP · cooperative predator prey / MPE | accumulated reward | Improved |
| use VIP instead of discrete-time MADDPG under varying time intervals | coupled oscillator · Coupled oscillator, varying time interval | average return | Improved |
| increase injected dynamics noise (sigma^2 0.1 to 1.0) (ablation) | VIP · Predator-Prey and Cooperative Navigation | performance | Hurt |
| increase time step Delta t beyond about 0.15 (ablation) | VIP · Coupled oscillator | average return | Hurt |
Closest papers by meaning
- Value Iteration in Continuous Actions, States and Time (ICML 2021 · similarity 0.90)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training (NeurIPS 2024 · similarity 0.88)
- Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control (NeurIPS 2025 · similarity 0.88)
- A Temporal Difference Method for Stochastic Continuous Dynamics (NeurIPS 2025 · similarity 0.87)
- SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning (AAAI 2025 · similarity 0.87)
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.
