The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent years. Deep Reinforcement Learning has been used extensively in these settings, as it does not have the unsustainable training costs associated with supervised learning. However, DeepRL suffers from poor sample efficiency, i.e., it requires a large number of environmental interactions to converge to an acceptable solution. Modern RL algorithms such as Deep Q Learning and Soft Actor-Critic attempt to remedy this shortcoming but can not provide the explainability required in applications such as autonomous robotics. Humans intuitively understand the long-time-horizon sequential tasks common in robotics. Properly using such intuition can make RL policies more explainable while enhancing their sample efficiency. In this work, we propose SHIRE, a novel framework for encoding human intuition using Probabilistic Graphical Models (PGMs) and using it in the Deep RL training pipeline to enhance sample efficiency. Our framework achieves 25-78% sample efficiency gains across the environments we evaluate at negligible overhead cost. Additionally, by teaching RL agents the encoded elementary behavior, SHIRE enhances policy explainability. A real-world demonstration further highlights the efficacy of policies trained using our framework.

In a reinforcement learning (RL) setting, the agent's optimal strategy heavily depends on her risk preferences and the underlying model dynamics of the training environment. These two aspects influence the agent's ability to make well-informed and time-consistent decisions when facing testing environments. In this work, we devise a framework to solve robust risk-aware RL problems where we simultaneously account for environmental uncertainty and risk with a class of dynamic robust distortion risk measures. Robustness is introduced by considering all models within a Wasserstein ball around a reference model. We estimate such dynamic robust risk measures using neural networks by making use of strictly consistent scoring functions, derive policy gradient formulae using the quantile representation of distortion risk measures, and construct an actor-critic algorithm to solve this class of robust risk-aware RL problems. We demonstrate the performance of our algorithm on a portfolio allocation example.

Although deep reinforcement learning (DRL) approaches in audio signal processing have seen substantial progress in recent years, audio-driven DRL for tasks such as navigation, gaze control and head-orientation control in the context of human-robot interaction have received little attention. Here, we propose an audio-driven DRL framework in which we utilise deep Q-learning to develop an autonomous agent that orients towards a talker in the acoustic environment based on stereo speech recordings. Our results show that the agent learned to perform the task at a near perfect level when trained on speech segments in anechoic environments (that is, without reverberation). The presence of reverberation in naturalistic acoustic environments affected the agent's performance, although the agent still substantially outperformed a baseline, randomly acting agent. Finally, we quantified the degree of generalization of the proposed DRL approach across naturalistic acoustic environments. Our experiments revealed that policies learned by agents trained on medium or high reverb environments generalized to low reverb environments, but policies learned by agents trained on anechoic or low reverb environments did not generalize to medium or high reverb environments. Taken together, this study demonstrates the potential of audio-driven DRL for tasks such as head-orientation control and highlights the need for training strategies that enable robust generalization across environments for real-world audio-driven DRL applications.

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational efficiency, our algorithm for linear MDPs achieves the best-known regret upper bound of $\widetilde{\mathcal{O}}(d^{3/2}\mathrm{sp}(v^*)\sqrt{T})$ over $T$ time steps where $\mathrm{sp}(v^*)$ is the span of the optimal bias function $v^*$ and $d$ is the dimension of the feature mapping. For linear mixture MDPs, our algorithm attains a regret bound of $\widetilde{\mathcal{O}}(d\cdot\mathrm{sp}(v^*)\sqrt{T})$. The algorithm applies novel techniques to control the covering number of the value function class and the span of optimistic estimators of the value function, which is of independent interest.

The Job Shop Scheduling Problem (JSSP) is a complex combinatorial optimization problem. There has been growing interest in using online Reinforcement Learning (RL) for JSSP. While online RL can quickly find acceptable solutions, especially for larger problems, it produces lower-quality results than traditional methods like Constraint Programming (CP). A significant downside of online RL is that it cannot learn from existing data, such as solutions generated from CP, requiring them to train from scratch, leading to sample inefficiency and making them unable to learn from more optimal examples. We introduce Offline Reinforcement Learning for Learning to Dispatch (Offline-LD), a novel approach for JSSP that addresses these limitations. Offline-LD adapts two CQL-based Q-learning methods (mQRDQN and discrete mSAC) for maskable action spaces, introduces a new entropy bonus modification for discrete SAC, and exploits reward normalization through preprocessing. Our experiments show that Offline-LD outperforms online RL on both generated and benchmark instances. By introducing noise into the dataset, we achieve similar or better results than those obtained from the expert dataset, indicating that a more diverse training set is preferable because it contains counterfactual information.

Robot navigation is increasingly crucial across applications like delivery services and warehouse management. The integration of Reinforcement Learning (RL) with classical planning has given rise to meta-planners that combine the adaptability of RL with the explainable decision-making of classical planners. However, the exploration capabilities of RL-based meta-planners during training are often constrained by the capabilities of the underlying classical planners. This constraint can result in limited exploration, thereby leading to sampling skew issues. To address these issues, our paper introduces a novel framework, DIGIMON, which begins with behavior-guided diagnosis for exploration bottlenecks within the meta-planner and follows up with a mitigation strategy that conducts up-sampling from diagnosed bottleneck data. Our evaluation shows 13.5%+ improvement in navigation performance, greater robustness in out-of-distribution environments, and a 4x boost in training efficiency. DIGIMON is designed as a versatile, plug-and-play solution, allowing seamless integration into various RL-based meta-planners.

Autonomous mobile robots are increasingly employed in pedestrian-rich environments where safe navigation and appropriate human interaction are crucial. While Deep Reinforcement Learning (DRL) enables socially integrated robot behavior, challenges persist in novel or perturbed scenarios to indicate when and why the policy is uncertain. Unknown uncertainty in decision-making can lead to collisions or human discomfort and is one reason why safe and risk-aware navigation is still an open problem. This work introduces a novel approach that integrates aleatoric, epistemic, and predictive uncertainty estimation into a DRL-based navigation framework for uncertainty estimates in decision-making. We, therefore, incorporate Observation-Dependent Variance (ODV) and dropout into the Proximal Policy Optimization (PPO) algorithm. For different types of perturbations, we compare the ability of Deep Ensembles and Monte-Carlo Dropout (MC-Dropout) to estimate the uncertainties of the policy. In uncertain decision-making situations, we propose to change the robot's social behavior to conservative collision avoidance. The results show that the ODV-PPO algorithm converges faster with better generalization and disentangles the aleatoric and epistemic uncertainties. In addition, the MC-Dropout approach is more sensitive to perturbations and capable to correlate the uncertainty type to the perturbation type better. With the proposed safe action selection scheme, the robot can navigate in perturbed environments with fewer collisions.

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which has a bias towards immediate gratification. Quasi-Hyperbolic (QH) discounting is a simple alternative for modeling this bias. Unlike in traditional discounting, though, the optimal QH-policy, starting from some time $t_1,$ can be different to the one starting from $t_2.$ Hence, the future self of an agent, if it is naive or impatient, can deviate from the policy that is optimal at the start, leading to sub-optimal overall returns. To prevent this behavior, an alternative is to work with a policy anchored in a Markov Perfect Equilibrium (MPE). In this work, we propose the first model-free algorithm for finding an MPE. Using a two-timescale analysis, we show that, if our algorithm converges, then the limit must be an MPE. We also validate this claim numerically for the standard inventory system with stochastic demands. Our work significantly advances the practical application of reinforcement learning.

This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online means that in each learning episode, the said environment is stabilized. This, as demonstrated in a case study with a mobile robot simulator, greatly improves the overall learning performance. The base actor-critic scheme of CALF is analogous to SARSA. The latter did not show any success in reaching the target in our studies. However, a modified version thereof, called SARSA-m here, did succeed in some learning scenarios. Still, CALF greatly outperformed the said approach. CALF was also demonstrated to improve a nominal stabilizer provided to it. In summary, the presented agent may be considered a viable approach to fusing classical control with reinforcement learning. Its concurrent approaches are mostly either offline or model-based, like, for instance, those that fuse model-predictive control into the agent.

This paper explores the application of Reinforcement Learning (RL) to the two-dimensional rectangular packing problem. We propose a reduced representation of the state and action spaces that allow us for high granularity. Leveraging UNet architecture and Proximal Policy Optimization (PPO), we achieved a model that is comparable to the MaxRect heuristic. However, our approach has great potential to be generalized to nonrectangular packing problems and complex constraints.