Game development is a long process that involves many stages before a product is ready for the market. Human play testing is among the most time consuming, as testers are required to repeatedly perform tasks in the search for errors in the code. Therefore, automated testing is seen as a key technology for the gaming industry, as it would dramatically improve development costs and efficiency. Toward this end, we propose EVOLUTE, a novel imitation learning-based architecture that combines behavioural cloning (BC) with energy based models (EBMs). EVOLUTE is a two-stream ensemble model that splits the action space of autonomous agents into continuous and discrete tasks. The EBM stream handles the continuous tasks, to have a more refined and adaptive control, while the BC stream handles discrete actions, to ease training. We evaluate the performance of EVOLUTE in a shooting-and-driving game, where the agent is required to navigate and continuously identify targets to attack. The proposed model has higher generalisation capabilities than standard BC approaches, showing a wider range of behaviours and higher performances. Also, EVOLUTE is easier to train than a pure end-to-end EBM model, as discrete tasks can be quite sparse in the dataset and cause model training to explore a much wider set of possible actions while training.

Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate them deterministically, assuming compliance with the reposition. In this paper, we consider a more realistic and driver-centric scenario where drivers have unique cruising preferences and can decide whether to take the recommendation or not on their own. We propose i-Rebalance, a personalized vehicle reposition technique with deep reinforcement learning (DRL). i-Rebalance estimates drivers' decisions on accepting reposition recommendations through an on-field user study involving 99 real drivers. To optimize supply-demand balance and enhance preference satisfaction simultaneously, i-Rebalance has a sequential reposition strategy with dual DRL agents: Grid Agent to determine the reposition order of idle vehicles, and Vehicle Agent to provide personalized recommendations to each vehicle in the pre-defined order. This sequential learning strategy facilitates more effective policy training within a smaller action space compared to traditional joint-action methods. Evaluation of real-world trajectory data shows that i-Rebalance improves driver acceptance rate by 38.07% and total driver income by 9.97%.

The Stochastic Approximation (SA) algorithm introduced by Robbins and Monro in 1951 has been a standard method for solving equations of the form $\mathbf{f}({\boldsymbol {\theta}}) = \mathbf{0}$, when only noisy measurements of $\mathbf{f}(\cdot)$ are available. If $\mathbf{f}({\boldsymbol {\theta}}) = \nabla J({\boldsymbol {\theta}})$ for some function $J(\cdot)$, then SA can also be used to find a stationary point of $J(\cdot)$. At each time $t$, the current guess ${\boldsymbol {\theta}}_t$ is updated to ${\boldsymbol {\theta}}_{t+1}$ using a noisy measurement of the form $\mathbf{f}({\boldsymbol {\theta}}_t) + {\boldsymbol {\xi}}_{t+1}$. In much of the literature, it is assumed that the error term ${\boldsymbol {\xi}}_{t+1}$ has zero conditional mean, and/or that its conditional variance is bounded as a function of $t$ (though not necessarily with respect to ${\boldsymbol {\theta}}_t$). Over the years, SA has been applied to a variety of areas, out of which the focus in this paper is on convex and nonconvex optimization. As it turns out, in these applications, the above-mentioned assumptions on the measurement error do not always hold. In zero-order methods, the error neither has zero mean nor bounded conditional variance. In the present paper, we extend SA theory to encompass errors with nonzero conditional mean and/or unbounded conditional variance. In addition, we derive estimates for the rate of convergence of the algorithm, and compute the ``optimal step size sequences'' to maximize the estimated rate of convergence.

Autonomous surface vessels (ASVs) play an increasingly important role in the safety and sustainability of open sea operations. Since most maritime accidents are related to human failure, intelligent algorithms for autonomous collision avoidance and path following can drastically reduce the risk in the maritime sector. A DT is a virtual representative of a real physical system and can enhance the situational awareness (SITAW) of such an ASV to generate optimal decisions. This work builds on an existing DT framework for ASVs and demonstrates foundations for enabling predictive, prescriptive, and autonomous capabilities. In this context, sophisticated target tracking approaches are crucial for estimating and predicting the position and motion of other dynamic objects. The applied tracking method is enabled by real-time automatic identification system (AIS) data and synthetic light detection and ranging (Lidar) measurements. To guarantee safety during autonomous operations, we applied a predictive safety filter, based on the concept of nonlinear model predictive control (NMPC). The approaches are implemented into a DT built with the Unity game engine. As a result, this work demonstrates the potential of a DT capable of making predictions, playing through various what-if scenarios, and providing optimal control decisions according to its enhanced SITAW.

Deep reinforcement learning (RL) has been shown to be effective in producing approximate solutions to some vehicle routing problems (VRPs), especially when using policies generated by encoder-decoder attention mechanisms. While these techniques have been quite successful for relatively simple problem instances, there are still under-researched and highly complex VRP variants for which no effective RL method has been demonstrated. In this work we focus on one such VRP variant, which contains multiple trucks and multi-leg routing requirements. In these problems, demand is required to move along sequences of nodes, instead of just from a start node to an end node. With the goal of making deep RL a viable strategy for real-world industrial-scale supply chain logistics, we develop new extensions to existing encoder-decoder attention models which allow them to handle multiple trucks and multi-leg routing requirements. Our models have the advantage that they can be trained for a small number of trucks and nodes, and then embedded into a large supply chain to yield solutions for larger numbers of trucks and nodes. We test our approach on a real supply chain environment arising in the operations of Japanese automotive parts manufacturer Aisin Corporation, and find that our algorithm outperforms Aisin's previous best solution.

The authors of 'Unsupervised Reinforcement Learning in Multiple environments' propose a method, alpha-MEPOL, to tackle unsupervised RL across multiple environments. They pre-train a task-agnostic exploration policy using interactions from an entire environment class and then fine-tune this policy for various tasks using supervision. We expanded upon this work, with the goal of improving performance. We primarily propose and experiment with five new modifications to the original work: sampling trajectories using an entropy-based probability distribution, dynamic alpha, higher KL Divergence threshold, curiosity-driven exploration, and alpha-percentile sampling on curiosity. Dynamic alpha and higher KL-Divergence threshold both provided a significant improvement over the baseline from the earlier work. PDF-sampling failed to provide any improvement due to it being approximately equivalent to the baseline method when the sample space is small. In high-dimensional environments, the addition of curiosity-driven exploration enhances learning by encouraging the agent to seek diverse experiences and explore the unknown more. However, its benefits are limited in low-dimensional and simpler environments where exploration possibilities are constrained and there is little that is truly unknown to the agent. Overall, some of our experiments did boost performance over the baseline and there are a few directions that seem promising for further research.

We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is therefore rather simple to implement. Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction. To achieve the preceding qualities, we build upon the concept of a Minimax Winner (MW), a notion of preference aggregation from the social choice theory literature that frames learning from preferences as a zero-sum game between two policies. By leveraging the symmetry of this game, we prove that rather than using the traditional technique of dueling two policies to compute the MW, we can simply have a single agent play against itself while maintaining strong convergence guarantees. Practically, this corresponds to sampling multiple trajectories from a policy, asking a rater or preference model to compare them, and then using the proportion of wins as the reward for a particular trajectory. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches while maintaining robustness to the intransitive and stochastic preferences that frequently occur in practice when aggregating human judgments.

In recent years, DNNs have shown promising results This paper describes methods for training autonomous in the field of behavioural cloning (BC) [5, 18]. BC is a agents to play the game "Doom 2" through Imitation form of Imitation Learning (IL), where we train an artificial Learning (IL) using only pixel data as input. We also explore "agent" to mimic actions from an observable state of how Reinforcement Learning (RL) compares to IL expert data [34]. Agents are trained using a number of historical for humanness by comparing camera movement and trajectory states, be they image frames or other data, and their data. Through behavioural cloning, we examine the corresponding actions. The learning is performed by using ability of individual models to learn varying behavioural the final frame's associated action as the "target", this target traits. We attempt to mimic the behaviour of real players being passed to some loss function. The loss function will with different play styles, and find we can train agents that reinforce the observed frame's predicted action, doing this behave aggressively, passively, or simply more human-like over an extremely large dataset will achieve an agent that than traditional AIs. We propose these methods of introducing can predict the best action to take at any one given set of more depth and human-like behaviour to agents in video input image frames [17].

The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.

Accurate mapping of greenhouse gas fluxes at the Earth's surface is essential for the validation and calibration of climate models. In this study, we present a framework for surface flux estimation with drones. Our approach uses data assimilation (DA) to infer fluxes from drone-based observations, and reinforcement learning (RL) to optimize the drone's sampling strategy. Herein, we demonstrate that a RL-trained drone can quantify a CO2 hotspot more accurately than a drone sampling along a predefined flight path that traverses the emission plume. We find that information-based reward functions can match the performance of an error-based reward function that quantifies the difference between the estimated surface flux and the true value. Reward functions based on information gain and information entropy can motivate actions that increase the drone's confidence in its updated belief, without requiring knowledge of the true surface flux. These findings provide valuable insights for further development of the framework for the mapping of more complex surface flux fields.