Reinforcement learning (RL) problems where the learner attempts to infer an unobserved reward from some feedback variables have been studied in several recent papers. The setting of Interaction-Grounded Learning (IGL) is an example of such feedback-based RL tasks where the learner optimizes the return by inferring latent binary rewards from the interaction with the environment. In the IGL setting, a relevant assumption used in the RL literature is that the feedback variable $Y$ is conditionally independent of the context-action $(X,A)$ given the latent reward $R$. In this work, we propose Variational Information-based IGL (VI-IGL) as an information-theoretic method to enforce the conditional independence assumption in the IGL-based RL problem. The VI-IGL framework learns a reward decoder using an information-based objective based on the conditional mutual information (MI) between $(X,A)$ and $Y$. To estimate and optimize the information-based terms for the continuous random variables in the RL problem, VI-IGL leverages the variational representation of mutual information to obtain a min-max optimization problem. Also, we extend the VI-IGL framework to general $f$-Information measures leading to the generalized $f$-VI-IGL framework for the IGL-based RL problems. We present numerical results on several reinforcement learning settings indicating an improved performance compared to the existing IGL-based RL algorithm.

Parallel Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources, allowing for faster generation of samples, estimation of values, and policy improvement. These computational paradigms require a seamless integration of training, serving, and simulation workloads. Existing frameworks, such as Ray, are not managing this orchestration efficiently, especially in RL tasks that demand intensive input/output and synchronization between actors on a single node. In this study, we have proposed a solution implementing the reactor model, which enforces a set of actors to have a fixed communication pattern. This allows the scheduler to eliminate work needed for synchronization, such as acquiring and releasing locks for each actor or sending and processing coordination-related messages. Our framework, Lingua Franca (LF), a coordination language based on the reactor model, also supports true parallelism in Python and provides a unified interface that allows users to automatically generate dataflow graphs for RL tasks. In comparison to Ray on a single-node multi-core compute platform, LF achieves 1.21x and 11.62x higher simulation throughput in OpenAI Gym and Atari environments, reduces the average training time of synchronized parallel Q-learning by 31.2%, and accelerates multi-agent RL inference by 5.12x.

Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of a deep learning (DL) model. However, designing such a single-step model is always challenging, requiring a huge number of parameters and easily falling into bad global minimums and overfitting. In this work, we reformulate I2IT as a step-wise decision-making problem via deep reinforcement learning (DRL) and propose a novel framework that performs RL-based I2IT (RL-I2IT). The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image. Considering that it is challenging to handle high dimensional continuous state and action spaces in the conventional RL framework, we introduce meta policy with a new concept Plan to the standard Actor-Critic model, which is of a lower dimension than the original image and can facilitate the actor to generate a tractable high dimensional action. In the RL-I2IT framework, we also employ a task-specific auxiliary learning strategy to stabilize the training process and improve the performance of the corresponding task. Experiments on several I2IT tasks demonstrate the effectiveness and robustness of the proposed method when facing high-dimensional continuous action space problems. Our implementation of the RL-I2IT framework is available at https://github.com/Algolzw/SPAC-Deformable-Registration.

Machine Unlearning is an emerging field that addresses data privacy issues by enabling the removal of private or irrelevant data from the Machine Learning process. Challenges related to privacy and model efficiency arise from the use of outdated, private, and irrelevant data. These issues compromise both the accuracy and the computational efficiency of models in both Machine Learning and Unlearning. To mitigate these challenges, we introduce a novel framework, Attention-based Machine Unlearning using Federated Reinforcement Learning (FRAMU). This framework incorporates adaptive learning mechanisms, privacy preservation techniques, and optimization strategies, making it a well-rounded solution for handling various data sources, either single-modality or multi-modality, while maintaining accuracy and privacy. FRAMU's strength lies in its adaptability to fluctuating data landscapes, its ability to unlearn outdated, private, or irrelevant data, and its support for continual model evolution without compromising privacy. Our experiments, conducted on both single-modality and multi-modality datasets, revealed that FRAMU significantly outperformed baseline models. Additional assessments of convergence behavior and optimization strategies further validate the framework's utility in federated learning applications. Overall, FRAMU advances Machine Unlearning by offering a robust, privacy-preserving solution that optimizes model performance while also addressing key challenges in dynamic data environments.

Reinforcement learning is well known for its ability to model sequential tasks and learn latent data patterns adaptively. Deep learning models have been widely explored and adopted in regression and classification tasks. However, deep learning has its limitations such as the assumption of equally spaced and ordered data, and the lack of ability to incorporate graph structure in terms of time-series prediction. Graphical neural network (GNN) has the ability to overcome these challenges and capture the temporal dependencies in time-series data. In this study, we propose a novel approach for predicting time-series data using GNN and monitoring with Reinforcement Learning (RL). GNNs are able to explicitly incorporate the graph structure of the data into the model, allowing them to capture temporal dependencies in a more natural way. This approach allows for more accurate predictions in complex temporal structures, such as those found in healthcare, traffic and weather forecasting. We also fine-tune our GraphRL model using a Bayesian optimisation technique to further improve performance. The proposed framework outperforms the baseline models in time-series forecasting and monitoring. The contributions of this study include the introduction of a novel GraphRL framework for time-series prediction and the demonstration of the effectiveness of GNNs in comparison to traditional deep learning models such as RNNs and LSTMs. Overall, this study demonstrates the potential of GraphRL in providing accurate and efficient predictions in dynamic RL environments.

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across tasks is important as it determines an agent's adaptability to real-world scenarios where reward mechanisms might vary. In this work, we first show that training a general world model can utilize similar structures in these tasks and help train more generalizable agents. Extending world models into the task generalization setting, we introduce a novel method named Task Aware Dreamer (TAD), which integrates reward-informed features to identify consistent latent characteristics across tasks. Within TAD, we compute the variational lower bound of sample data log-likelihood, which introduces a new term designed to differentiate tasks using their states, as the optimization objective of our reward-informed world models. To demonstrate the advantages of the reward-informed policy in TAD, we introduce a new metric called Task Distribution Relevance (TDR) which quantitatively measures the relevance of different tasks. For tasks exhibiting a high TDR, i.e., the tasks differ significantly, we illustrate that Markovian policies struggle to distinguish them, thus it is necessary to utilize reward-informed policies in TAD. Extensive experiments in both image-based and state-based tasks show that TAD can significantly improve the performance of handling different tasks simultaneously, especially for those with high TDR, and display a strong generalization ability to unseen tasks.

Recent advancements in deep reinforcement learning (DRL) techniques have sparked its multifaceted applications in the automation sector. Managing complex decision-making problems with DRL encourages its use in the nuclear industry for tasks such as optimizing radiation exposure to the personnel during normal operating conditions and potential accidental scenarios. However, the lack of efficient reward function and effective exploration strategy thwarted its implementation in the development of radiation-aware autonomous unmanned aerial vehicle (UAV) for achieving maximum radiation protection. Here, in this article, we address these intriguing issues and introduce a deep Q-learning based architecture (RadDQN) that operates on a radiation-aware reward function to provide time-efficient minimum radiation-exposure pathway in a radiation zone. We propose a set of unique exploration strategies that fine-tune the extent of exploration and exploitation based on the state-wise variation in radiation exposure during training. Further, we benchmark the predicted path with grid-based deterministic method. We demonstrate that the formulated reward function in conjugation with adequate exploration strategy is effective in handling several scenarios with drastically different radiation field distributions. When compared to vanilla DQN, our model achieves a superior convergence rate and higher training stability.

Alan Turing proposed in 1950 a framework called an imitation game to decide if a machine could think. Using mathematics developed largely after Turing -- category theory -- we analyze a broader class of universal imitation games (UIGs), which includes static, dynamic, and evolutionary games. In static games, the participants are in a steady state. In dynamic UIGs, "learner" participants are trying to imitate "teacher" participants over the long run. In evolutionary UIGs, the participants are competing against each other in an evolutionary game, and participants can go extinct and be replaced by others with higher fitness. We use the framework of category theory -- in particular, two influential results by Yoneda -- to characterize each type of imitation game. Universal properties in categories are defined by initial and final objects. We characterize dynamic UIGs where participants are learning by inductive inference as initial algebras over well-founded sets, and contrast them with participants learning by conductive inference over the final coalgebra of non-well-founded sets. We briefly discuss the extension of our categorical framework for UIGs to imitation games on quantum computers.

In a recent computational framework called active inference, discrete models can be linked to their continuous counterparts to perform decision-making in changing environments. From another perspective, simple agents can be combined to better capture the causal relationships of the world. How can we use these two features together to achieve efficient goal-directed behavior? We present an architecture composed of several hybrid -- continuous and discrete -- units replicating the agent's configuration, controlled by a high-level discrete model that achieves dynamic planning and synchronized behavior. Additional factorizations within each level allow to represent hierarchically other agents and objects in relation to the self. We evaluate this hierarchical hybrid model on a non-trivial task: reaching a moving object after having picked a moving tool. This study extends past work on control as inference and proposes an alternative direction to deep reinforcement learning.

This paper considers the problem of multi-agent reinforcement learning (multi-agent RL), where multiple agents aim to make decisions simultaneously in an unfamiliar environment to maximize their individual cumulative rewards. Multi-agent RL is used not only in large-scale strategy games like Go [Silver et al., 2017], Poker [Brown and Sandholm, 2019] and MOBA games [Ye et al., 2020], but also in various real-world applications such as autonomous driving[Shalev-Shwartz et al., 2016], household power management [Chung et al., 2020], and computer networking[Bhattacharyya et al., 2019]. The sheer amount of computation needed for self-play-based learning in these applications often demands the algorithm to run in a distributed fashion where the communication cost becomes a bottleneck. In such circumstances, instead of syncing up after each single trajectory, a more practical alternative is to assign a larger batch of work for each machine to perform independently and sync up only sporadically. The need for infrequent communication could be hard constraints in applications such as autonomous driving [Shalev-Shwartz et al., 2016]. Deploying new policies to vehicle firmware takes weeks, while new data are being collected in millions of cars every second. These constraints render standard multi-agent RL algorithms that require altering the policy after each new data point impractical. In the scenarios discussed above, the agent needs to minimize the number of policy deployments while learning a good policy using (nearly) the same number of samples as its fully-adaptive counterparts.