Reinforcement learning of real-world tasks is very data inefficient, and extensive simulation-based modelling has become the dominant approach for training systems. However, in human-robot interaction and many other real-world settings, there is no appropriate one-model-for-all due to differences in individual instances of the system (e.g. different people) or necessary oversimplifications in the simulation models. This requires two approaches: 1. either learning the individual system's dynamics approximately from data which requires data-intensive training or 2. using a complete digital twin of the instances, which may not be realisable in many cases. We introduce two approaches: co-kriging adjustments (CKA) and ridge regression adjustment (RRA) as novel ways to combine the advantages of both approaches. Our adjustment methods are based on an auto-regressive AR1 co-kriging model that we integrate with GP priors. This yield a data- and simulation-efficient way of using simplistic simulation models (e.g., simple two-link model) and rapidly adapting them to individual instances (e.g., biomechanics of individual people). Using CKA and RRA, we obtain more accurate uncertainty quantification of the entire system's dynamics than pure GP-based and AR1 methods. We demonstrate the efficiency of co-kriging adjustment with an interpretable reinforcement learning control example, learning to control a biomechanical human arm using only a two-link arm simulation model (offline part) and CKA derived from a small amount of interaction data (on-the-fly online). Our method unlocks an efficient and uncertainty-aware way to implement reinforcement learning methods in real world complex systems for which only imperfect simulation models exist.

This study explores the potential of reinforcement learning algorithms to enhance career planning processes. Leveraging data from Randstad The Netherlands, the study simulates the Dutch job market and develops strategies to optimize employees' long-term income. By formulating career planning as a Markov Decision Process (MDP) and utilizing machine learning algorithms such as Sarsa, Q-Learning, and A2C, we learn optimal policies that recommend career paths with high-income occupations and industries. The results demonstrate significant improvements in employees' income trajectories, with RL models, particularly Q-Learning and Sarsa, achieving an average increase of 5% compared to observed career paths. The study acknowledges limitations, including narrow job filtering, simplifications in the environment formulation, and assumptions regarding employment continuity and zero application costs. Future research can explore additional objectives beyond income optimization and address these limitations to further enhance career planning processes.

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on maximizing a reward function, which typically captures general trends but cannot precisely capture, or rule out, certain behaviors of the system. In this paper, we propose a novel framework aimed at drastically reducing the undesirable behavior of DRL-based software, while maintaining its excellent performance. In addition, our framework can assist in providing engineers with a comprehensible characterization of such undesirable behavior. Under the hood, our approach is based on extracting decision tree classifiers from erroneous state-action pairs, and then integrating these trees into the DRL training loop, penalizing the system whenever it performs an error. We provide a proof-of-concept implementation of our approach, and use it to evaluate the technique on three significant case studies. We find that our approach can extend existing frameworks in a straightforward manner, and incurs only a slight overhead in training time. Further, it incurs only a very slight hit to performance, or even in some cases -- improves it, while significantly reducing the frequency of undesirable behavior.

Non-differentiable controllers and rule-based policies are widely used for controlling real systems such as telecommunication networks and robots. Specifically, parameters of mobile network base station antennas can be dynamically configured by these policies to improve users coverage and quality of service. Motivated by the antenna tilt control problem, we introduce Model-Based Residual Policy Learning (MBRPL), a practical reinforcement learning (RL) method. MBRPL enhances existing policies through a model-based approach, leading to improved sample efficiency and a decreased number of interactions with the actual environment when compared to off-the-shelf RL methods.To the best of our knowledge, this is the first paper that examines a model-based approach for antenna control. Experimental results reveal that our method delivers strong initial performance while improving sample efficiency over previous RL methods, which is one step towards deploying these algorithms in real networks.

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of the matrix underlying the projected TD fixed point. Our analysis shows that tail-averaged TD converges at the optimal $O\left(1/t\right)$ rate, both in expectation and with high probability. In addition, our bounds exhibit a sharper rate of decay for the initial error (bias), which is an improvement over averaging all iterates. We also propose and analyse a variant of TD that incorporates regularisation. From analysis, we conclude that the regularised version of TD is useful for problems with ill-conditioned features.

Model-based reinforcement learning (MBRL) with real-time planning has shown great potential in locomotion and manipulation control tasks. However, the existing planning methods, such as the Cross-Entropy Method (CEM), do not scale well to complex high-dimensional environments. One of the key reasons for underperformance is the lack of exploration, as these planning methods only aim to maximize the cumulative extrinsic reward over the planning horizon. Furthermore, planning inside the compact latent space in the absence of observations makes it challenging to use curiosity-based intrinsic motivation. We propose Curiosity CEM (CCEM), an improved version of the CEM algorithm for encouraging exploration via curiosity. Our proposed method maximizes the sum of state-action Q values over the planning horizon, in which these Q values estimate the future extrinsic and intrinsic reward, hence encouraging reaching novel observations. In addition, our model uses contrastive representation learning to efficiently learn latent representations. Experiments on image-based continuous control tasks from the DeepMind Control suite show that CCEM is by a large margin more sample-efficient than previous MBRL algorithms and compares favorably with the best model-free RL methods.

Optimizing for humans' latent preferences remains a grand challenge in route recommendation. Prior research has provided increasingly general techniques based on inverse reinforcement learning (IRL), yet no approach has been successfully scaled to world-sized routing problems with hundreds of millions of states and demonstration trajectories. In this paper, we provide methods for scaling IRL using graph compression, spatial parallelization, and problem initialization based on dominant eigenvectors. We revisit classic algorithms and study them in a large-scale setting, and make the key observation that there exists a trade-off between the use of cheap, deterministic planners and expensive yet robust stochastic policies. We leverage this insight in Receding Horizon Inverse Planning (RHIP), a new generalization of classic IRL algorithms that provides fine-grained control over performance trade-offs via its planning horizon. Our contributions culminate in a policy that achieves a 16-24% improvement in global route quality, and to the best of our knowledge, represents the largest instance of IRL in a real-world setting to date. Benchmark results show critical benefits to more sustainable modes of transportation, where factors beyond journey time play a substantial role. We conclude by conducting an ablation study of key components, presenting negative results from alternative eigenvalue solvers, and identifying opportunities to further improve scalability via IRL-specific batching strategies.

We present the effect of adapting to human preferences on trust in a human-robot teaming task. The team performs a task in which the robot acts as an action recommender to the human. It is assumed that the behavior of the human and the robot is based on some reward function they try to optimize. We use a new human trust-behavior model that enables the robot to learn and adapt to the human's preferences in real-time during their interaction using Bayesian Inverse Reinforcement Learning. We present three strategies for the robot to interact with a human: a non-learner strategy, in which the robot assumes that the human's reward function is the same as the robot's, a non-adaptive learner strategy that learns the human's reward function for performance estimation, but still optimizes its own reward function, and an adaptive-learner strategy that learns the human's reward function for performance estimation and also optimizes this learned reward function. Results show that adapting to the human's reward function results in the highest trust in the robot.

The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of optimal control. The main contributions firstly concern properties of the relaxation, described as a deterministic convex program: we identify conditions for a bounded solution, and a significant relationship between the solution to the new convex program, and the solution to standard Q-learning. The second set of contributions concern algorithm design and analysis: (i) A direct model-free method for approximating the convex program for Q-learning shares properties with its ideal. In particular, a bounded solution is ensured subject to a simple property of the basis functions; (ii) The proposed algorithms are convergent and new techniques are introduced to obtain the rate of convergence in a mean-square sense; (iii) The approach can be generalized to a range of performance criteria, and it is found that variance can be reduced by considering ``relative'' dynamic programming equations; (iv) The theory is illustrated with an application to a classical inventory control problem.

Drones are becoming versatile in a myriad of applications. This has led to the use of drones for spying and intruding into the restricted or private air spaces. Such foul use of drone technology is dangerous for the safety and security of many critical infrastructures. In addition, due to the varied low-cost design and agility of the drones, it is a challenging task to identify and track them using the conventional radar systems. In this paper, we propose a reinforcement learning based approach for identifying and tracking any intruder drone using a chaser drone. Our proposed solution uses computer vision techniques interleaved with the policy learning framework of reinforcement learning to learn a control policy for chasing the intruder drone. The whole system has been implemented using ROS and Gazebo along with the Ardupilot based flight controller. The results show that the reinforcement learning based policy converges to identify and track the intruder drone. Further, the learnt policy is robust with respect to the change in speed or orientation of the intruder drone.