Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming

Despite tremendous progress, machine learning and deep learning still suffer from incomprehensible predictions. Incomprehensibility, however, is not an option for the use of (deep) reinforcement learning in the real world, as unpredictable actions can seriously harm the involved individuals. In this work, we propose a genetic programming framework to generate explanations for the decision-making process of already trained agents by imitating them with programs. Programs are interpretable and can be executed to generate explanations of why the agent chooses a particular action. Furthermore, we conduct an ablation study that investigates how extending the domain-specific language by using library learning alters the performance of the method. We compare our results with the previous state of the art for this problem and show that we are comparable in performance but require much less hardware resources and computation time.

Decentralized Task Offloading and Load-Balancing for Mobile Edge Computing in Dense Networks

We study the problem of decentralized task offloading and load-balancing in a dense network with numerous devices and a set of edge servers. Solving this problem optimally is complicated due to the unknown network information and random task sizes. The shared network resources also influence the users' decisions and resource distribution. Our solution combines the mean field multi-agent multi-armed bandit (MAB) game with a load-balancing technique that adjusts the servers' rewards to achieve a target population profile despite the distributed user decision-making. Numerical results demonstrate the efficacy of our approach and the convergence to the target load distribution.

Distributed Management of Fluctuating Energy Resources in Dynamic Networked Systems

Modern power systems integrate renewable distributed energy resources (DERs) as an environment-friendly enhancement to meet the ever-increasing demands. However, the inherent unreliability of renewable energy renders developing DER management algorithms imperative. We study the energy-sharing problem in a system consisting of several DERs. Each agent harvests and distributes renewable energy in its neighborhood to optimize the network's performance while minimizing energy waste. We model this problem as a bandit convex optimization problem with constraints that correspond to each node's limitations for energy production. We propose distributed decision-making policies to solve the formulated problem, where we utilize the notion of dynamic regret as the performance metric. We also include an adjustment strategy in our developed algorithm to reduce the constraint violations. Besides, we design a policy that deals with the non-stationary environment. Theoretical analysis shows the effectiveness of our proposed algorithm. Numerical experiments using a real-world dataset show superior performance of our proposal compared to state-of-the-art methods.

Budgeted Recommendation with Delayed Feedback

In a conventional contextual multi-armed bandit problem, the feedback (or reward) is immediately observable after an action. Nevertheless, delayed feedback arises in numerous real-life situations and is particularly crucial in time-sensitive applications. The exploration-exploitation dilemma becomes particularly challenging under such conditions, as it couples with the interplay between delays and limited resources. Besides, a limited budget often aggravates the problem by restricting the exploration potential. A motivating example is the distribution of medical supplies at the early stage of COVID-19. The delayed feedback of testing results, thus insufficient information for learning, degraded the efficiency of resource allocation. Motivated by such applications, we study the effect of delayed feedback on constrained contextual bandits. We develop a decision-making policy, delay-oriented resource allocation with learning (DORAL), to optimize the resource expenditure in a contextual multi-armed bandit problem with arm-dependent delayed feedback.

Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation

Representation rank is an important concept for understanding the role of Neural Networks (NNs) in Deep Reinforcement learning (DRL), which measures the expressive capacity of value networks. Existing studies focus on unboundedly maximizing this rank; nevertheless, that approach would introduce overly complex models in the learning, thus undermining performance. Hence, fine-tuning representation rank presents a challenging and crucial optimization problem. To address this issue, we find a guiding principle for adaptive control of the representation rank. We employ the Bellman equation as a theoretical foundation and derive an upper bound on the cosine similarity of consecutive state-action pairs representations of value networks. We then leverage this upper bound to propose a novel regularizer, namely BEllman Equation-based automatic rank Regularizer (BEER). This regularizer adaptively regularizes the representation rank, thus improving the DRL agent's performance. We first validate the effectiveness of automatic control of rank on illustrative experiments. Then, we scale up BEER to complex continuous control tasks by combining it with the deterministic policy gradient method. Among 12 challenging DeepMind control tasks, BEER outperforms the baselines by a large margin. Besides, BEER demonstrates significant advantages in Q-value approximation. Our code is available at https://github.com/sweetice/BEER-ICLR2024.

Meta Learning in Bandits within Shared Affine Subspaces

We study the problem of meta-learning several contextual stochastic bandits tasks by leveraging their concentration around a low-dimensional affine subspace, which we learn via online principal component analysis to reduce the expected regret over the encountered bandits. We propose and theoretically analyze two strategies that solve the problem: One based on the principle of optimism in the face of uncertainty and the other via Thompson sampling. Our framework is generic and includes previously proposed approaches as special cases. Besides, the empirical results show that our methods significantly reduce the regret on several bandit tasks.

Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments

Understanding the interactions of agents trained with deep reinforcement learning is crucial for deploying agents in games or the real world. In the former, unreasonable actions confuse players. In the latter, that effect is even more significant, as unexpected behavior cause accidents with potentially grave and long-lasting consequences for the involved individuals. In this work, we propose using program synthesis to imitate reinforcement learning policies after seeing a trajectory of the action sequence. Programs have the advantage that they are inherently interpretable and verifiable for correctness. We adapt the state-of-the-art program synthesis system DreamCoder for learning concepts in grid-based environments, specifically, a navigation task and two miniature versions of Atari games, Space Invaders and Asterix. By inspecting the generated libraries, we can make inferences about the concepts the black-box agent has learned and better understand the agent's behavior. We achieve the same by visualizing the agent's decision-making process for the imitated sequences. We evaluate our approach with different types of program synthesizers based on a search-only method, a neural-guided search, and a language model fine-tuned on code.

Federated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization

Federated learning (FL) involves several devices that collaboratively train a shared model without transferring their local data. FL reduces the communication overhead, making it a promising learning method in UAV-enhanced wireless networks with scarce energy resources. Despite the potential, implementing FL in UAV-enhanced networks is challenging, as conventional UAV placement methods that maximize coverage increase the FL delay significantly. Moreover, the uncertainty and lack of a priori information about crucial variables, such as channel quality, exacerbate the problem. In this paper, we first analyze the statistical characteristics of a UAV-enhanced wireless sensor network (WSN) with energy harvesting. We then develop a model and solution based on the multi-objective multi-armed bandit theory to maximize the network coverage while minimizing the FL delay. Besides, we propose another solution that is particularly useful with large action sets and strict energy constraints at the UAVs. Our proposal uses a scalarized best-arm identification algorithm to find the optimal arms that maximize the ratio of the expected reward to the expected energy cost by sequentially eliminating one or more arms in each round. Then, we derive the upper bound on the error probability of our multi-objective and cost-aware algorithm. Numerical results show the effectiveness of our approach.

Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards

We study the piecewise stationary combinatorial semi-bandit problem with causally related rewards. In our nonstationary environment, variations in the base arms' distributions, causal relationships between rewards, or both, change the reward generation process. In such an environment, an optimal decision-maker must follow both sources of change and adapt accordingly. The problem becomes aggravated in the combinatorial semi-bandit setting, where the decision-maker only observes the outcome of the selected bundle of arms. The core of our proposed policy is the Upper Confidence Bound (UCB) algorithm. We assume the agent relies on an adaptive approach to overcome the challenge. More specifically, it employs a change-point detector based on the Generalized Likelihood Ratio (GLR) test. Besides, we introduce the notion of group restart as a new alternative restarting strategy in the decision making process in structured environments. Finally, our algorithm integrates a mechanism to trace the variations of the underlying graph structure, which captures the causal relationships between the rewards in the bandit setting. Theoretically, we establish a regret upper bound that reflects the effects of the number of structural- and distribution changes on the performance. The outcome of our numerical experiments in real-world scenarios exhibits applicability and superior performance of our proposal compared to the state-of-the-art benchmarks.

Online Learning with Costly Features in Non-stationary Environments

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before making a decision. In real-world problems, however, collecting beneficial information is often costly. That implies that, besides individual arms' reward, learning the observations of the features' states is essential to improve the decision-making strategy. The problem is aggravated in a non-stationary environment where reward and cost distributions undergo abrupt changes over time. To address the aforementioned dual learning problem, we extend the contextual bandit setting and allow the agent to observe subsets of features' states. The objective is to maximize the long-term average gain, which is the difference between the accumulated rewards and the paid costs on average. Therefore, the agent faces a trade-off between minimizing the cost of information acquisition and possibly improving the decision-making process using the obtained information. To this end, we develop an algorithm that guarantees a sublinear regret in time. Numerical results demonstrate the superiority of our proposed policy in a real-world scenario.