Riccardo Zamboni

Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni et al.

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and decentralised coordination. Genuinely solving such tasks requires Dec-POMDP reasoning, where agents use history to infer hidden states and coordinate based on local information. Yet it remains unclear whether popular benchmarks actually demand this reasoning or permit success via simpler strategies. We introduce a diagnostic suite combining statistically grounded performance comparisons and information-theoretic probes to audit the behavioural complexity of baseline policies (IPPO and MAPPO) across 37 scenarios spanning MPE, SMAX, Overcooked, Hanabi, and MaBrax. Our diagnostics reveal that success on these benchmarks rarely requires genuine Dec-POMDP reasoning. Reactive policies match the performance of memory-based agents in over half the scenarios, and emergent coordination frequently relies on brittle, synchronous action coupling rather than robust temporal influence. These findings suggest that some widely used benchmarks may not adequately test core Dec-POMDP assumptions under current training paradigms, potentially leading to over-optimistic assessments of progress. We release our diagnostic tooling to support more rigorous environment design and evaluation in cooperative MARL.

Andrea Fraschini, Davide Tenedini, Riccardo Zamboni et al.

Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework, which we refer to as Action-based Policy Compression (APC), mitigates this issue by compressing the parameter space $Θ$ into a low-dimensional latent manifold $\mathcal Z$ using a learned generative mapping $g:\mathcal Z \to Θ$. However, its performance is severely constrained by relying on immediate action-matching as a reconstruction loss, a myopic proxy for behavioral similarity that suffers from compounding errors across sequential decisions. To overcome this bottleneck, we introduce Occupancy-based Policy Compression (OPC), which enhances APC by shifting behavior representation from immediate action-matching to long-horizon state-space coverage. Specifically, we propose two principal improvements: (1) we curate the dataset generation with an information-theoretic uniqueness metric that delivers a diverse population of policies; and (2) we propose a fully differentiable compression objective that directly minimizes the divergence between the true and reconstructed mixture occupancy distributions. These modifications force the generative model to organize the latent space around true functional similarity, promoting a latent representation that generalizes over a broad spectrum of behaviors while retaining most of the original parameter space's expressivity. Finally, we empirically validate the advantages of our contributions across multiple continuous control benchmarks.

Vincenzo De Paola, Mirco Mutti, Riccardo Zamboni et al.

Parallelization in Reinforcement Learning is typically employed to speed up the training of a single policy, where multiple workers collect experience from an identical sampling distribution. This common design limits the potential of parallelization by neglecting the advantages of diverse exploration strategies. We propose K-Myriad, a scalable and unsupervised method that maximizes the collective state entropy induced by a population of parallel policies. By cultivating a portfolio of specialized exploration strategies, K-Myriad provides a robust initialization for Reinforcement Learning, leading to both higher training efficiency and the discovery of heterogeneous solutions. Experiments on high-dimensional continuous control tasks, with large-scale parallelization, demonstrate that K-Myriad can learn a broad set of distinct policies, highlighting its effectiveness for collective exploration and paving the way towards novel parallelization strategies.

Marcel Hedman, Kale-ab Abebe Tessera, Juan Claude Formanek et al.

Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data converge to suboptimal joint behaviours because they cannot co-adapt as their policies change. We introduce CODA (Coordination via On-Policy Diffusion for Multi-Agent Reinforcement Learning), a diffusion-based multi-agent trajectory generator for data augmentation that samples conditioned on the current joint policy, producing synthetic experience which reflects the evolving behaviours of the agents, thereby providing a mechanism for co-adaptation. We find that previous diffusion-based augmentation approaches are insufficient for fostering multi-agent coordination because they produce static augmented datasets that do not evolve as the current joint policy changes during training; CODA resolves this by more closely simulating on-policy learning and is a meaningful step toward coordinated behaviours in the offline setting. CODA is algorithm-agnostic and can be layered onto both model-free and model-based offline reinforcement learning pipelines as an augmentation module. Empirically, CODA not only resolves canonical coordination pathologies in continuous polynomial games but also delivers strong results on the more complex MaMuJoCo continuous-control benchmarks.

Riccardo Zamboni, Mirco Mutti, Marcello Restelli

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks. In single-agent settings, the problem has been extensively studied and mostly understood. A popular approach, called task-agnostic exploration, casts the unsupervised objective as maximizing the entropy of the state distribution induced by the agent's policy, from which principles and methods follow. In contrast, little is known about it in multi-agent settings, which are ubiquitous in the real world. What are the pros and cons of alternative problem formulations in this setting? How hard is the problem in theory, how can we solve it in practice? In this paper, we address these questions by first characterizing those alternative formulations and highlighting how the problem, even when tractable in theory, is non-trivial in practice. Then, we present a scalable, decentralized, trust-region policy search algorithm to address the problem in practical settings. Finally, we provide numerical validations to both corroborate the theoretical findings and pave the way for unsupervised multi-agent reinforcement learning via task-agnostic exploration in challenging domains, showing that optimizing for a specific objective, namely mixture entropy, provides an excellent trade-off between tractability and performances.

Vincenzo De Paola, Riccardo Zamboni, Mirco Mutti et al.

Parallel data collection has redefined Reinforcement Learning (RL), unlocking unprecedented efficiency and powering breakthroughs in large-scale real-world applications. In this paradigm, $N$ identical agents operate in $N$ replicas of an environment simulator, accelerating data collection by a factor of $N$. A critical question arises: \textit{Does specializing the policies of the parallel agents hold the key to surpass the $N$ factor acceleration?} In this paper, we introduce a novel learning framework that maximizes the entropy of collected data in a parallel setting. Our approach carefully balances the entropy of individual agents with inter-agent diversity, effectively minimizing redundancies. The latter idea is implemented with a centralized policy gradient method, which shows promise when evaluated empirically against systems of identical agents, as well as synergy with batch RL techniques that can exploit data diversity. Finally, we provide an original concentration analysis that shows faster rates for specialized parallel sampling distributions, which supports our methodology and may be of independent interest.

Davide Tenedini, Riccardo Zamboni, Mirco Mutti et al.

Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant parameter space $Θ$. This challenge is greatly compounded in multi-task settings. In this work, we develop a novel, unsupervised approach that compresses the policy parameter space $Θ$ into a low-dimensional latent space $\mathcal{Z}$. We train a generative model $g:\mathcal{Z}\toΘ$ by optimizing a behavioral reconstruction loss, which ensures that the latent space is organized by functional similarity rather than proximity in parameterization. We conjecture that the inherent dimensionality of this manifold is a function of the environment's complexity, rather than the size of the policy network. We validate our approach in continuous control domains, showing that the parameterization of standard policy networks can be compressed up to five orders of magnitude while retaining most of its expressivity. As a byproduct, we show that the learned manifold enables task-specific adaptation via Policy Gradient operating in the latent space $\mathcal{Z}$.

Kale-ab Abebe Tessera, Leonard Hinckeldey, Riccardo Zamboni et al.

Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In practice, current model-free MARL algorithms use simple recurrent function approximators to address the challenge of reasoning about others using partial information. In this position paper, we argue that the empirical success of these methods is not due to effective Markov signal recovery, but rather to learning simple conventions that bypass environment observations and memory. Through a targeted case study, we show that co-adapting agents can learn brittle conventions, which then fail when partnered with non-adaptive agents. Crucially, the same models can learn grounded policies when the task design necessitates it, revealing that the issue is not a fundamental limitation of the learning models but a failure of the benchmark design. Our analysis also suggests that modern MARL environments may not adequately test the core assumptions of Dec-POMDPs. We therefore advocate for new cooperative environments built upon two core principles: (1) behaviours grounded in observations and (2) memory-based reasoning about other agents, ensuring success requires genuine skill rather than fragile, co-adapted agreements.

Riccardo Zamboni, Enrico Brunetti, Marcello Restelli

Offline Reinforcement Learning (RL) focuses on learning policies solely from a batch of previously collected data. offering the potential to leverage such datasets effectively without the need for costly or risky active exploration. While recent advances in Offline Multi-Agent RL (MARL) have shown promise, most existing methods either rely on large datasets jointly collected by all agents or agent-specific datasets collected independently. The former approach ensures strong performance but raises scalability concerns, while the latter emphasizes scalability at the expense of performance guarantees. In this work, we propose a novel scalable routine for both dataset collection and offline learning. Agents first collect diverse datasets coherently with a pre-specified information-sharing network and subsequently learn coherent localized policies without requiring either full observability or falling back to complete decentralization. We theoretically demonstrate that this structured approach allows a multi-agent extension of the seminal Fitted Q-Iteration (FQI) algorithm to globally converge, in high probability, to near-optimal policies. The convergence is subject to error terms that depend on the informativeness of the shared information. Furthermore, we show how this approach allows to bound the inherent error of the supervised-learning phase of FQI with the mutual information between shared and unshared information. Our algorithm, SCAlable Multi-agent FQI (SCAM-FQI), is then evaluated on a distributed decision-making problem. The empirical results align with our theoretical findings, supporting the effectiveness of SCAM-FQI in achieving a balance between scalability and policy performance.

Riccardo Zamboni, Duilio Cirino, Marcello Restelli et al.

The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied. However, little attention has been dedicated to state entropy maximization under partial observability, despite the latter being ubiquitous in applications, e.g., finance and robotics, in which the agent only receives noisy observations of the true state governing the system's dynamics. How can we address state entropy maximization in those domains? In this paper, we study the simple approach of maximizing the entropy over observations in place of true latent states. First, we provide lower and upper bounds to the approximation of the true state entropy that only depends on some properties of the observation function. Then, we show how knowledge of the latter can be exploited to compute a principled regularization of the observation entropy to improve performance. With this work, we provide both a flexible approach to bring advances in state entropy maximization to the POMDP setting and a theoretical characterization of its intrinsic limits.

Riccardo Zamboni, Duilio Cirino, Marcello Restelli et al.

Recent works have studied *state entropy maximization* in reinforcement learning, in which the agent's objective is to learn a policy inducing high entropy over states visitation (Hazan et al., 2019). They typically assume full observability of the state of the system, so that the entropy of the observations is maximized. In practice, the agent may only get *partial* observations, e.g., a robot perceiving the state of a physical space through proximity sensors and cameras. A significant mismatch between the entropy over observations and true states of the system can arise in those settings. In this paper, we address the problem of entropy maximization over the *true states* with a decision policy conditioned on partial observations *only*. The latter is a generalization of POMDPs, which is intractable in general. We develop a memory and computationally efficient *policy gradient* method to address a first-order relaxation of the objective defined on *belief* states, providing various formal characterizations of approximation gaps, the optimization landscape, and the *hallucination* problem. This paper aims to generalize state entropy maximization to more realistic domains that meet the challenges of applications.