Sequential MARL

Fully decentralized multi-agent reinforcement learning (MARL), also referred to as independent learning, requires each agent to learn and act using only its local information and experience, without a centralized critic or inter-agent communication. Such a stringent information structure renders the conventional reward signal ambiguous. A poor return may result from an ineffective ego action, an incompatible teammate response, or an effective opponent response, yet scalar rewards alone do not reveal which explanation is responsible. We argue that agents can learn more effectively by prospectively comparing the consequences of candidate actions rather than diagnosing failures only from realized returns. We introduce CASTLE (Counterfactual Action-conditioned Semantic Tokens for Local Execution in Decentralized MARL), an offline-training, online-in-context guidance framework with two complementary world models. A Local Dynamics World Model, offline pre-trained over agents' local trajectories, summarizes the agent's local trajectory dynamics and partial observability, while a Semantic-Social World Model predicts compact short-horizon task and social consequences for each candidate ego action. The latter is trained from counterfactual simulator rollouts that expose plausible teammate and opponent responses to alternative actions taken from the same logged rollout state. During online learning and execution, both world models remain frozen and are queried by agents using only locally available information. Their prediction logits provide in-context guidance to an independent PPO policy. Across 30 matched seeds on Tag, Spread, and Adversary in the benchmark multi-particle environments, our proposed CASTLE achieves the highest mean final score among the evaluated methods, exceeding the strongest baseline on each task by 10.67, 6.46, and 0.33 normalized points, respectively.

Rate-limited multi-agent teams raise three questions the emergent-communication literature has answered only empirically: what an optimal message should encode, what compression costs over a horizon, and when a learned protocol is unique enough for a teammate to read. We answer them for rate-limited Dec-POMDPs, then measure how far reinforcement learning falls short of the optimum. Our theorems fix what is achievable independently of any learner, so a gap between an engineered and a learned sender at the same bit budget is an optimization fact, not an information-theoretic one. We instantiate this on three MuJoCo arenas spanning zero, partial and rigid physical coupling, charging every condition exactly 2 bits per decision, and create the discriminating regime by closing a physical side channel within one arena, holding bodies, task and reward fixed. Communication value is governed by coupling: under rigid coupling through a shared object, no channel beats silence (+0.001 +/- 0.001, p = 0.982, n = 25), since proprioception already carries that information; without coupling, every condition solves the task; under partial coupling, the engineered 2-bit sender reaches an interquartile mean of 1.000 but the learned one reaches 0.482, indistinguishable from silence (p = 0.400, n = 25). With a shared alphabet, bandwidth cannot explain the gap. Warm-starting from an engineered receiver localizes the failure: the same channel reaches 0.857 versus 0.562 cold-started (p < 0.001), so it is neither representational nor one of maintenance; reinforcement learning fails to discover the protocol. Cross-play shows learned protocols are individually meaningful but mutually unintelligible: self-play 0.980 collapses to 0.144 across seeds, and our best constructed alignment leaves at least 77% of that gap. All headline results use 25 seeds per arena and seven published baselines at matched rate.

Robots deployed for competitive tasks must outmaneuver their opponents without sacrificing safety. Existing approaches, including safe reinforcement learning (RL), train a single policy to achieve task success and avoid failures simultaneously. This coupling can complicate training and leave the learned policy exploitable by deliberate attacks. We propose Safety to Competence (S2C), a two-stage RL framework that separates safety synthesis from competitive task learning. We formulate competitive interactions as safety-critical Markov games and prove that perfect filtering preserves policy non-exploitability when all players commit to safe maneuvers. S2C learns a robust safety filter via adversarial RL, embeds it in the environment during task policy training, and retains the same filter at deployment. In simulated touchdown games, S2C outperforms eight safe RL baselines, achieving the highest win rate and Elo rating, and the lowest exploitability. Hardware stress tests against a human opponent confirm S2C's competence.

Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.

This letter proposes the Predictive Lightweight Multi-Agent Reinforcement Learning (PL-MARL) framework to ensure resilient coverage in bandwidth-constrained UAV swarms. To counter coordination collapse caused by sparse signaling and information aging, we introduce a Kinematic-Aware Inference Engine that proactively reconstructs neighbor trajectories via physical priors. This approach enables an efficient computation-for-communication trade-off, decoupling structural resilience from signaling frequency. Simulations confirm that PL-MARL maintains superior coverage and mission continuity under extreme signaling scarcity and node failure. Our results validate proactive inference as a scalable, low-latency solution for robust aerial coordination, effectively minimizing control overhead to preserve spectrum for payload services while ensuring resilience against interference.

Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grades only the final answer. On hard problems this trains models to write more rather than to think better, since the trace itself is never graded and no label for good thinking exists. We introduce Agon, which makes two competing models each other's graders. Both attempt the same problem; in alternating roles, one drafts a solution and the other reads it while solving, and each is rewarded for out-solving the other. To win, a model must out-reason a rival that has seen its work, so reasoning is judged implicitly during training, with no process labels and no reward model. Because both models are optimized, each faces a progressively stronger rival, which single-model RL cannot provide. The two need only be comparably strong and behaviorally different. At inference the pair deploys as it trains, a two-stage cascade in which one model drafts and the other answers after reading the draft. On the hard split of DeepMath with Qwen3, this doubles GRPO's pass@1, roughly eight times the gain of an untrained Mixture-of-Agents pass over the same base. The ordering replicates on competitive-programming code and across model families (Qwen3.5, Gemma 4). For now the models talk in text; the next step is to let them reason together in latent space.

Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent. Instead of relying on other agents' actions, the independent actors setting considers each agent to act based only on its local information, thus having more flexible applications. However, in the sequential update framework, it is required to re-estimate the joint advantage function after each individual agent's policy step. Despite the practical success of importance sampling, the updated advantage function suffers from exponentially high variance problems, which likely result in unstable convergence. In this work, we first analyze the high variance advantage both empirically and theoretically. To overcome this limitation, we introduce a clipping objective to control the upper bounds of the advantage fluctuation in sequential updates. With the proposed objective, we provide a monotonic bound with sub-linear convergence to $ε$-Nash Equilibria. We further derive two new practical algorithms using our clipping objective. The experiment results on three popular multi-agent reinforcement learning benchmarks show that our proposed method outperforms the tested baselines in most environments. By carefully analyzing different training settings, our proposed method is highlighted with both stable convergence properties and the desired low advantage variance estimation. For reproducibility purposes, our source code is publicly available at https://github.com/giangbang/Low-Variance-Trust-Region-MARL.

Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and \emph{``Flat''} RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4% vs 51.5% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

Multi-Agent Systems (MAS) have emerged as a fundamental paradigm for distributed problem-solving, where autonomous agents collaborate to achieve complex objectives. Within this framework, Multi-Agent Reinforcement Learning (MARL) with communication has demonstrated remarkable success in cooperative tasks. However, existing approaches predominantly pursue performance gains through increasingly complex architectures and expanding communication overhead, lacking principled metrics to evaluate the efficiency of information exchange. In this paper, we focus on enabling agents to learn efficient multi-agent communication protocols that balance performance and information compactness. We propose the Information Entropy Efficiency Index (IEI), a novel metric that quantifies the ratio between message entropy and task performance in learned communication protocols. A lower IEI indicates more compact and efficient message representations. By incorporating IEI into training loss functions, we encourage agents to develop communication protocols that achieve high performance with improved communication efficiency. Extensive experiments across diverse MARL algorithms demonstrate that our approach achieves equivalent or superior task performance compared to baseline methods while improving communication efficiency. These findings challenge the prevailing assumption that performance improvements require complex architectures or increased communication overhead and highlight the potential of improving both task success and communication efficiency to enable scalable MAS.

We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function of that artifact and its own private state, and no centralized learner accesses joint trajectories -- the operating regime of multi-agent LLM pipelines that span organizational, vendor, or trust boundaries. We formalize this regime as an interface-constrained semi-Markov decision process (IC-SMDP), whose decision epochs occur at handoff times, and design IC-$Q$, an asynchronous decentralized $Q$-learning algorithm in which cross-agent coordination at every handoff is exactly one scalar. Our main result is a finite-sample bound for neural IC-$Q$ that decomposes into three independently controllable error sources: neural function-approximation error, interface representation gap, and a mixing-time residual, under the random option-duration discount. Establishing this bound requires lifting the approximate information state (AIS) framework from single-agent primitive-step MDPs to multi-agent SMDPs and controlling Markovian noise under random duration, neither of which has been done in prior work. To our knowledge this is the first finite-sample guarantee for neural $Q$-learning under decentralized partial observability. Four experiments: a controlled synthetic IC-SMDP that validates the bound term-by-term, multi-LLM mathematical reasoning, multi-agent routing, and multi-agent CPU programming, show that IC-$Q$ matches a centralized oracle without any agent observing joint trajectories, with each of the three error sources scaling along its corresponding axis as the bound predicts.

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that limit generalization. In contrast, large language models (LLMs) offer a flexible modeling interface that can naturally accommodate heterogeneous observations and actions. Motivated by this, we propose the Decision Language Model (DLM), which formulates multi-agent decision making as a dialogue-style sequence prediction problem under the centralized training with decentralized execution paradigm. DLM is trained in two stages: a supervised fine-tuning phase, which leverages dialogue-style datasets for centralized training with inter-agent context and generates executable actions from offline trajectories, followed by a group relative policy optimization phase to enhance robustness to out-of-distribution actions through lightweight reward functions. Experiments on multiple benchmarks show that a unified DLM outperforms strong offline MARL baselines and LLM-based conversational decision-making methods, while demonstrating strong zero-shot generalization to unseen scenarios across tasks.

In cooperative teams where agents act in a fixed order and share a single team-level reward (multi-agent language systems, sequential robotic tasks), per-agent credit assignment is under-determined. Critic-based approaches scale poorly as the number of agents grows owing to the costly maintenance of joint/factored critic(s), whereas the existing critic-free alternatives have other issues: common credit across agents that couples every agent's signal to teammate noise, importance-sampling corrections for upstream-update staleness that incur variance exponential in team size, or per-agent counterfactual replay that isolates each agent's effect at the price of extra environment or reward calls. We propose COSAC, a critic-free per-agent policy gradient for sequential cooperative teams. COSAC fits an additive per-agent decomposition of the team reward by a single ridge regression on the rollout batch (giving each agent a learning signal decoupled from teammate noise), and computes each agent's counterfactual advantage from fictitious continuations of the current policy (policy forward passes that replace both importance-sampling reweighting and per-agent environment replay, at no extra environment or reward cost). The estimator instantiates the Sequential Aristocrat Utility (SeqAU), our extension of Wolpert and Tumer's (2001) aristocrat utility to sequential teams. We prove bias and variance bounds on SeqAU credits that stay controlled as the team grows. Our controlled study on sequential bandits demonstrates that COSAC attains the lowest advantage MSE and consistently low learning regret across team sizes up to $K = 16$. On the AI2 Reasoning Challenge (ARC) task, where four Qwen3-0.6B agents reason in turn about a grade-school science question, COSAC attains faster convergence than the other critic-free baselines.