G2MAF is a test‑time refinement framework for offline multi‑agent reinforcement learning that applies a single globally normalized, projected critic gradient to adjust all agents’ actions while keeping them close to a frozen policy proposal. The method improves performance on 24 Multi‑Party Environment (MPE) and StarCraft Multi‑Agent Challenge (SMAC) benchmarks, achieving mean relative gains of 9.2% on MPE and 8.9% on SMAC, with only a 6% increase in inference latency.
arXiv:2606. 11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.
arXiv:2602. 21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
The paper introduces MA-WAM, a test‑time planning framework that uses a frozen multi‑agent flow policy to evaluate future joint actions by predicting their consequences while accounting for cross‑agent dependencies. Unlike naive extensions of single‑agent world models, MA‑WAM captures the interactions among simultaneous actions, enabling efficient candidate scoring. Experiments on 30 MARL benchmarks (MAMuJoCo, SMAC, MPE) show MA‑WAM improves performance by 22.0% over direct execution and 25.6% over uniform action selection, with only a 12.1 ms overhead on an A100 GPU.
arXiv:2606. 30072v1 Announce Type: new Abstract: Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return.
arXiv:2609.36812v1 Announce Type: cross Abstract: Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the beha...
arXiv:2605.01457v4 Announce Type: replace Abstract: How can generative offline multi-agent reinforcement learning achieve both fast joint trajectory generation and effective cooperation? Multi-agent...
arXiv:2508. 13661v4 Announce Type: replace Abstract: Centralized Training with Decentralized Execution (CTDE) is the dominant paradigm in multi-agent reinforcement learning (MARL), enabling agents to act independently at test time while leveraging additional information during training.
Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions having high crit...
arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.
The paper introduces Multi-step Proximal Policy Improvement (MPI), a method that refines offline reinforcement learning policies through sequential re-centered proximal steps. By viewing policies as a probability manifold, MPI interprets a wide range of offline actor objectives as a single proximal policy improvement step and extends this to multiple steps for controlled policy improvement beyond the behavior distribution. Experiments on D4RL benchmarks demonstrate that a few MPI refinements enhance strong offline baselines such as TD3+BC, ReBRAC, and IQL, while diagnostics clarify the benefits of re-centered refinement over fixed-objective scheduling and highlight critic error limitations.
arXiv:2609.21108v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has achieved strong performance across a wide range of continuous-control problems. These continuous-control policies...