Policy-Conditioned Policies for Multi-Agent Task Solving

• URL: http://arxiv.org/abs/2512.21024v1
• Date: Wed, 24 Dec 2025 07:42:10 GMT
• Title: Policy-Conditioned Policies for Multi-Agent Task Solving
• Authors: Yue Lin, Shuhui Zhu, Wenhao Li, Ang Li, Dan Qiao, Pascal Poupart, Hongyuan Zha, Baoxiang Wang,
• Abstract summary: In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
• Score: 53.67744322553693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent deep reinforcement learning paradigm due to a fundamental ``representational bottleneck'': neural policies are opaque, high-dimensional parameter vectors that are incomprehensible to other agents. In this work, we propose a paradigm shift that bridges this gap by representing policies as human-interpretable source code and utilizing Large Language Models (LLMs) as approximate interpreters. This programmatic representation allows us to operationalize the game-theoretic concept of \textit{Program Equilibrium}. We reformulate the learning problem by utilizing LLMs to perform optimization directly in the space of programmatic policies. The LLM functions as a point-wise best-response operator that iteratively synthesizes and refines the ego agent's policy code to respond to the opponent's strategy. We formalize this process as \textit{Programmatic Iterated Best Response (PIBR)}, an algorithm where the policy code is optimized by textual gradients, using structured feedback derived from game utility and runtime unit tests. We demonstrate that this approach effectively solves several standard coordination matrix games and a cooperative Level-Based Foraging environment.

Related papers

• Learning Policy Representations for Steerable Behavior Synthesis [80.4542176039074]
  Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time.<n>We show that these representations can be approximated uniformly for a range of policies using a set-based architecture.<n>We use variational generative approach to induce a smooth latent space, and further shape it with contrastive learning so that latent distances align with differences in value functions.
  arXiv  Detail & Related papers  (2026-01-29T21:52:06Z)
• Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions [31.697208397735395]
  Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness.<n>We propose a solver-induced emphlatent spherical flow policy that brings the expressiveness of modern generative policies to the RL while guaranteeing feasibility by design.<n>Our approach outperforms state-of-the-art baselines by an average of 20.6% across a range of challenging RL tasks.
  arXiv  Detail & Related papers  (2026-01-29T18:49:07Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion [43.77763433288893]
  We introduce Contrastive Policy Gradient, or CoPG, a simple and mathematically principled new RL algorithm that can estimate the optimal policy even from off-policy data.<n>We show this approach to generalize the direct alignment method IPO (identity preference optimization) and classic policy gradient.<n>We experiment with the proposed CoPG on a toy bandit problem to illustrate its properties, as well as for finetuning LLMs on a summarization task.
  arXiv  Detail & Related papers  (2024-06-27T14:03:49Z)
• Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks [20.2777559515384]
  Programmatically Interpretable Reinforcement Learning (PIRL) encodes policies in human-readable computer programs. In this paper, we show that PIRL-specific algorithms are not needed, depending on the language used to encode the programmatic policies. We use a connection between ReLU neural networks and oblique decision trees to translate the policy learned with actor-critic algorithms into programmatic policies.
  arXiv  Detail & Related papers  (2023-08-04T22:17:32Z)
• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback [106.63518036538163]
  We present a novel unified bilevel optimization-based framework, textsfPARL, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning. Our framework addressed these concerns by explicitly parameterizing the distribution of the upper alignment objective (reward design) by the lower optimal variable. Our empirical results substantiate that the proposed textsfPARL can address the alignment concerns in RL by showing significant improvements.
  arXiv  Detail & Related papers  (2023-08-03T18:03:44Z)
• Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies [0.0]
  Policy optimization is the emphde facto paradigm to adapt robot policies as a function of task-specific objectives. We propose to leverage the structure of probabilistic policies by casting the policy optimization as an optimal transport problem. We evaluate our approach on common robotic settings: reaching motions, collision-avoidance behaviors, and multi-goal tasks.
  arXiv  Detail & Related papers  (2023-05-17T17:48:24Z)
• Multi-Task Off-Policy Learning from Bandit Feedback [54.96011624223482]
  We propose a hierarchical off-policy optimization algorithm (HierOPO), which estimates the parameters of the hierarchical model and then acts pessimistically with respect to them. We prove per-task bounds on the suboptimality of the learned policies, which show a clear improvement over not using the hierarchical model. Our theoretical and empirical results show a clear advantage of using the hierarchy over solving each task independently.
  arXiv  Detail & Related papers  (2022-12-09T08:26:27Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Composable Learning with Sparse Kernel Representations [110.19179439773578]
  We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment.
  arXiv  Detail & Related papers  (2021-03-26T13:58:23Z)

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.