Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn simultaneously and influence the underlying state as well as each others' observations. We propose the use of learned beliefs on the underlying state of the system to overcome these challenges and enable reinforcement learning with fully decentralized training and execution. Our approach leverages state information to pre-train a probabilistic belief model in a self-supervised fashion. The resulting belief states, which capture both inferred state information as well as uncertainty over this information, are then used in a state-based reinforcement learning algorithm to create an end-to-end model for cooperative multi-agent reinforcement learning under partial observability. By separating the belief and reinforcement learning tasks, we are able to significantly simplify the policy and value function learning tasks and improve both the convergence speed and the final performance. We evaluate our proposed method on diverse partially observable multi-agent tasks designed to exhibit different variants of partial observability.

Tradable credit schemes (TCS) are an increasingly studied alternative to congestion pricing, given their revenue neutrality and ability to address issues of equity through the initial credit allocation. Modeling TCS to aid future design and implementation is associated with challenges involving user and market behaviors, demand-supply dynamics, and control mechanisms. In this paper, we focus on the latter and address the day-to-day dynamic tolling problem under TCS, which is formulated as a discrete-time Markov Decision Process and solved using reinforcement learning (RL) algorithms. Our results indicate that RL algorithms achieve travel times and social welfare comparable to the Bayesian optimization benchmark, with generalization across varying capacities and demand levels. We further assess the robustness of RL under different hyperparameters and apply regularization techniques to mitigate action oscillation, which generates practical tolling strategies that are transferable under day-to-day demand and supply variability. Finally, we discuss potential challenges such as scaling to large networks, and show how transfer learning can be leveraged to improve computational efficiency and facilitate the practical deployment of RL-based TCS solutions.

In this paper, we study the offline sequential feature-based pricing and inventory control problem where the current demand depends on the past demand levels and any demand exceeding the available inventory is lost. Our goal is to leverage the offline dataset, consisting of past prices, ordering quantities, inventory levels, covariates, and censored sales levels, to estimate the optimal pricing and inventory control policy that maximizes long-term profit. While the underlying dynamic without censoring can be modeled by Markov decision process (MDP), the primary obstacle arises from the observed process where demand censoring is present, resulting in missing profit information, the failure of the Markov property, and a non-stationary optimal policy. To overcome these challenges, we first approximate the optimal policy by solving a high-order MDP characterized by the number of consecutive censoring instances, which ultimately boils down to solving a specialized Bellman equation tailored for this problem. Inspired by offline reinforcement learning and survival analysis, we propose two novel data-driven algorithms to solving these Bellman equations and, thus, estimate the optimal policy. Furthermore, we establish finite sample regret bounds to validate the effectiveness of these algorithms. Finally, we conduct numerical experiments to demonstrate the efficacy of our algorithms in estimating the optimal policy. To the best of our knowledge, this is the first data-driven approach to learning optimal pricing and inventory control policies in a sequential decision-making environment characterized by censored and dependent demand. The implementations of the proposed algorithms are available at https://github.com/gundemkorel/Inventory_Pricing_Control

-- This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Prior sim-to-real methods for legged robots mostly rely on the domain randomization approach, where a fixed finite set of simulation parameters is randomized during training. Instead, our method adds state-dependent perturbations to the input joint torque used for forward simulation during the training phase. These state-dependent perturbations are designed to simulate a broader range of reality gaps than those captured by randomizing a fixed set of simulation parameters. Experimental results show that our method enables humanoid locomotion policies that achieve greater robustness against complex reality gaps unseen in the training domain. Deep Reinforcement Learning (DRL) for robotic applications has gained significant attention due to its demonstrated robustness and versatility. Although DRL algorithms are capable of solving complex, high-dimensional control problems, commonly used on-policy methods often require a prohibitively large amount of data, posing a substantial challenge when collecting sufficient samples solely from real hardware. Moreover, the exploration process required for policy improvement in early training stages can raise safety concerns for both the physical robot and its operational environment.

Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive hyper-parameter tuning in data-driven methods. To address these challenges, we present Agent-Arena, a Python framework designed to streamline the integration, replication, development, and testing of decision-making policies across a wide range of benchmark environments. Unlike existing frameworks, Agent-Arena is uniquely generalised to support all types of control algorithms and is adaptable to both simulation and real-robot scenarios. Please see our GitHub repository https://github.com/halid1020/agent-arena-v0.

Restricted Boltzmann machines (RBMs) are energy-based models analogous to the Ising model and are widely applied in statistical machine learning. The standard inverse Ising problem with a complete dataset requires computing both data and model expectations and is computationally challenging because model expectations have a combinatorial explosion. Furthermore, in many applications, the available datasets are partially incomplete, making it difficult to compute even data expectations. In this study, we propose a approximation framework for these expectations in the practical inverse Ising problems that integrates mean-field approximation or persistent contrastive divergence to generate refined initial points and spatial Monte Carlo integration to enhance estimator accuracy. We demonstrate that the proposed method effectively and accurately tunes the model parameters in comparison to the conventional method.

Hierarchical inductive biases are hypothesized to promote generalizable policies in reinforcement learning, as demonstrated by explicit hyperbolic latent representations and architectures. Therefore, a more flexible approach is to have these biases emerge naturally from the algorithm. We introduce Free Random Projection, an input mapping grounded in free probability theory that constructs random orthogonal matrices where hierarchical structure arises inherently. The free random projection integrates seamlessly into existing in-context reinforcement learning frameworks by encoding hierarchical organization within the input space without requiring explicit architectural modifications. Empirical results on multi-environment benchmarks show that free random projection consistently outperforms the standard random projection, leading to improvements in generalization. Furthermore, analyses within linearly solvable Markov decision processes and investigations of the spectrum of kernel random matrices reveal the theoretical underpinnings of free random projection's enhanced performance, highlighting its capacity for effective adaptation in hierarchically structured state spaces.

Predicting future observations plays a central role in machine learning, biology, economics, and many other fields. It lies at the heart of organizational principles such as the variational free energy principle and has even been shown -- based on the second law of thermodynamics -- to be necessary for reaching the fundamental energetic limits of sequential information processing. While the usefulness of the predictive paradigm is undisputed, complex adaptive systems that interact with their environment are more than just predictive machines: they have the power to act upon their environment and cause change. In this work, we develop a framework to analyze the thermodynamics of information processing in percept-action loops -- a model of agent-environment interaction -- allowing us to investigate the thermodynamic implications of actions and percepts on equal footing. To this end, we introduce the concept of work capacity -- the maximum rate at which an agent can expect to extract work from its environment. Our results reveal that neither of two previously established design principles for work-efficient agents -- maximizing predictive power and forgetting past actions -- remains optimal in environments where actions have observable consequences. Instead, a trade-off emerges: work-efficient agents must balance prediction and forgetting, as remembering past actions can reduce the available free energy. This highlights a fundamental departure from the thermodynamics of passive observation, suggesting that prediction and energy efficiency may be at odds in active learning systems.

In the field of legged robot motion control, reinforcement learning (RL) holds great promise but faces two major challenges: high computational cost for training individual robots and poor generalization of trained models. To address these problems, this paper proposes a novel framework called Prior Transfer Reinforcement Learning (PTRL), which improves both training efficiency and model transferability across different robots. Drawing inspiration from model transfer techniques in deep learning, PTRL introduces a fine-tuning mechanism that selectively freezes layers of the policy network during transfer, making it the first to apply such a method in RL. The framework consists of three stages: pre-training on a source robot using the Proximal Policy Optimization (PPO) algorithm, transferring the learned policy to a target robot, and fine-tuning with partial network freezing. Extensive experiments on various robot platforms confirm that this approach significantly reduces training time while maintaining or even improving performance. Moreover, the study quantitatively analyzes how the ratio of frozen layers affects transfer results, providing valuable insights into optimizing the process. The experimental outcomes show that PTRL achieves better walking control performance and demonstrates strong generalization and adaptability, offering a promising solution for efficient and scalable RL-based control of legged robots.

Multi-agent reinforcement learning (MARL) has shown promise for adaptive traffic signal control (ATSC), enabling multiple intersections to coordinate signal timings in real time. However, in large-scale settings, MARL faces constraints due to extensive data sharing and communication requirements. Federated learning (FL) mitigates these challenges by training shared models without directly exchanging raw data, yet traditional FL methods such as FedAvg struggle with highly heterogeneous intersections. Different intersections exhibit varying traffic patterns, demands, and road structures, so performing FedAvg across all agents is inefficient. To address this gap, we propose Hierarchical Federated Reinforcement Learning (HFRL) for ATSC. HFRL employs clustering-based or optimization-based techniques to dynamically group intersections and perform FedAvg independently within groups of intersections with similar characteristics, enabling more effective coordination and scalability than standard FedAvg. Our experiments on synthetic and real-world traffic networks demonstrate that HFRL not only outperforms both decentralized and standard federated RL approaches but also identifies suitable grouping patterns based on network structure or traffic demand, resulting in a more robust framework for distributed, heterogeneous systems.