The paper introduces Turnover-Orthogonal Credit Assignment (TOCA), a method for open-team multi-agent reinforcement learning that separates the effects of agent actions, pure turnover, and action–turnover interactions in the team return. TOCA uses a permutation‑invariant centralized critic with event tokens to provide counterfactual per‑agent credit signals and a softly weighted interaction variant, TOCA‑β, for high‑variance environments. Experiments show that TOCA outperforms event‑aware MAPPO critics and that removing interaction credit degrades performance, especially in high‑turnover settings such as the Dynamic Spread benchmark.
arXiv:2610.08402v1 Announce Type: new Abstract: Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two r...
arXiv:2603. 21563v4 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding.
arXiv:2607. 17924v1 Announce Type: cross Abstract: Multi-agent policy optimization, exemplified by PPO-based methods, is a key branch of cooperative Multi-Agent Reinforcement Learning (MARL).
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
HySTAR is a MAPPO-based framework that addresses structural target drift in cooperative multi‑agent reinforcement learning by anchoring an overlapping sparse hypergraph as a stable high‑order value‑decomposition scaffold. It separates adaptive representation learning from a temporally consistent decomposition basis, using a spatiotemporal encoder to capture physical and task‑dependent interactions and combining temporal and structural relevance to compute agent‑specific advantages. Experiments on SMAC, GRF, Traffic Junction, and MPE show consistent improvements over MAPPO‑style, value‑factorization, and dynamic‑grouping baselines, achieving significant gains in performance and convergence speed.
The paper introduces TASPO, a method that transforms privileged information (PI) into outcome‑grounded action credit for language‑model agents. TASPO constructs decision‑applicable PI from verified successful experience, aggregates PI‑induced likelihood shifts at the executable‑action level, and converts relative action support into positive, bounded, mean‑preserving weights on the original trajectory advantage. Experiments on three agentic benchmarks show TASPO improves over GRPO by 10.6% and generalizes better to unseen tasks, while reducing supervision mismatch and stabilizing policy optimization.
arXiv:2601. 17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability.
arXiv:2606. 32017v1 Announce Type: cross Abstract: Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions.
arXiv:2511. 10687v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning.
arXiv:2608. 08255v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) often suffers from delayed and sparse rewards in real-world environments.
arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment o...