CAPO: Counterfactual Credit Assignment in Sequential Cooperative Teams

• URL: http://arxiv.org/abs/2604.17693v1
• Date: Mon, 20 Apr 2026 01:14:59 GMT
• Title: CAPO: Counterfactual Credit Assignment in Sequential Cooperative Teams
• Abstract summary: We introduce the Sequential Aristocrat Utility (SeqAU), the unique per-agent learning signal.<n>We derive CAPO, a critic-free policy-gradient algorithm.
• Score: 6.8920524670882815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In cooperative teams where agents act in a fixed order and share a single team reward, it is hard to know how much each agent contributed, and harder still when agents are updated one at a time because data collected earlier no longer reflects the new policies. We introduce the Sequential Aristocrat Utility (SeqAU), the unique per-agent learning signal that maximizes the individual learnability of each agent's action, extending the classical framework of Wolpert and Tumer (2002) to this sequential setting. From SeqAU we derive CAPO (Counterfactual Advantage Policy Optimization), a critic-free policy-gradient algorithm. CAPO fits a per-agent reward decomposition from group rewards and computes the per-agent advantage in closed form plus a handful of forward passes through the current policy, requiring no extra environment calls beyond the initial batch. We give analytic bias and variance bounds and validate them on a controlled sequential bandit, where CAPO's advantage over standard baselines grows with the team size. The framework is general; multi-LLM pipelines are a natural deployment target.

Related papers

• Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning [5.703301837612397]
  We show that multi-agent transfer can produce joint behavior strictly worse than every policy in the library.<n>We propose MA-USFA, a hierarchical method with two layers: a lower layer of universal successor feature approximators that predicts each agent's successor features while conditioned on its teammates' objectives, and an upper composer that selects, across agents, which library entry each agent should follow and supplies the cross-agent correction a per-agent value cannot represent.
  arXiv  Detail & Related papers  (2026-08-12T04:56:52Z)
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning [58.76655851910778]
  AgentOPSD is a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning.<n>We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B)
  arXiv  Detail & Related papers  (2026-08-06T13:00:59Z)
• ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning [47.96591344642519]
  Multi-Agent Reinforcement Learning requires agents to collectively maximize a shared return.<n>Prior methods largely follow two approaches: independent factorized updates with centralized critics, or alternating best-response updates.<n>We show the joint policy gradient admits an exact decentralized decomposition of per-agent terms, each formed from per-agent score functions and decentralized critics.<n>Central to this result is a serialized view of the simultaneous joint decision in which agents commit actions one at a time, each conditioning on a belief over preceding actions.
  arXiv  Detail & Related papers  (2026-06-29T10:04:15Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• Breaking $\ extit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• Counterfactual Credit Policy Optimization for Multi-Agent Collaboration [27.260904103460664]
  Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles and aggregating diverse hypotheses.<n>We introduce Counterfactual Credit Policy Optimization (CCPO), a framework that assigns agent-specific learning signals.<n> CCPO builds dynamic counterfactual baselines that simulate outcomes with an agent's contribution removed.
  arXiv  Detail & Related papers  (2026-03-23T04:35:02Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning [14.852334980733369]
  Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning.<n>We introduce Temporal-Agent Reward Redistribution (TAR$2$), an approach that decouples credit modeling from this constraint.<n>We demonstrate that this method is equivalent to a valid Potential-Based Reward Shaping (PBRS), which guarantees the optimal policy is preserved regardless of model accuracy.
  arXiv  Detail & Related papers  (2025-02-07T12:07:57Z)
• WARP: On the Benefits of Weight Averaged Rewarded Policies [66.95013068137115]
  We introduce a novel alignment strategy named Weight Averaged Rewarded Policies (WARP) WARP merges policies in the weight space at three distinct stages. Experiments with GEMMA policies validate that WARP improves their quality and alignment, outperforming other open-source LLMs.
  arXiv  Detail & Related papers  (2024-06-24T16:24:34Z)
• Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization [12.612009339150504]
  This work focuses on the entropy-regularized independent natural policy gradient (NPG) algorithm in multi-agent reinforcement learning. We show that, under sufficient entropy regularization, the dynamics of this system converge at a linear rate to the quantal response equilibrium (QRE)
  arXiv  Detail & Related papers  (2024-05-04T22:48:53Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)
• Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation [55.96893934962757]
  In multi-agent system, polices of different agents need to be evaluated jointly. In current methods, value functions or advantage functions use counter-factual joint actions which are evaluated asynchronously. In this work, we propose the approximatively synchronous advantage estimation.
  arXiv  Detail & Related papers  (2020-12-07T07:29:19Z)
• Multiagent Value Iteration Algorithms in Dynamic Programming and Reinforcement Learning [0.0]
  We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions. In an earlier work we introduced a policy iteration algorithm, where the policy improvement is done one-agent-at-a-time in a given order.
  arXiv  Detail & Related papers  (2020-05-04T16:34:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.