The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve a time-dependent orienteering problem with stochastic weights and time windows (TD-OPSWTW). It focused on two types of learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the setup of the competition, the winning methods, and give an overview of the results. The winning methods described in this work have advanced the state-of-the-art in using AI for stochastic routing problems. Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers. The simulator of the problem has been made open-source and can be used by other researchers as a benchmark for new AI methods.

Defects during production may lead to material waste, which is a significant challenge for many companies as it reduces revenue and negatively impacts sustainability and the environment. An essential reason for material waste is a low degree of automation, especially in industries that currently have a low degree of digitalization, such as steel forging. Those industries typically rely on heavy and old machinery such as large induction ovens that are mostly controlled manually or using well-known recipes created by experts. However, standard recipes may fail when unforeseen events happen, such as an unplanned stop in production, which may lead to overheating and thus material degradation during the forging process. In this paper, we develop a digital twin-based optimization strategy for the heating process for a forging line to automate the development of an optimal control policy that adjusts the power for the heating coils in an induction oven based on temperature data observed from pyrometers. We design a digital twin-based deep reinforcement learning (DTRL) framework and train two different deep reinforcement learning (DRL) models for the heating phase using a digital twin of the forging line. The twin is based on a simulator that contains a heating transfer and movement model, which is used as an environment for the DRL training. Our evaluation shows that both models significantly reduce the temperature unevenness and can help to automate the traditional heating process.

The environment is the setting that the agent is acting on and the agent represents the RL algorithm. To understand this better, let's suppose that our agent is learning to play counterstrike. The mathematical approach for mapping a solution in Reinforcement Learning is called Markov's Decision Process (MDP). To briefly sum it up, the agent must take an action (A) to transition from the start state to the end state (S). While doing so, the agent receives rewards (R) for each action he takes.

When people talk about artificial intelligence, they usually don't mean supervised and unsupervised machine learning. These tasks are pretty trivial compared to what we think of AIs doing - playing chess and Go, driving cars, and beating video games at a superhuman level. Reinforcement learning has recently become popular for doing all of that and more. Much like deep learning, a lot of the theory was discovered in the 70s and 80s but it hasn't been until recently that we've been able to observe first hand the amazing results that are possible. In 2016 we saw Google's AlphaGo beat the world Champion in Go. We saw AIs playing video games like Doom and Super Mario.

Subgraph matching is a fundamental problem in various fields that use graph structured data. Subgraph matching algorithms enumerate all isomorphic embeddings of a query graph q in a data graph G. An important branch of matching algorithms exploit the backtracking search approach which recursively extends intermediate results following a matching order of query vertices. It has been shown that the matching order plays a critical role in time efficiency of these backtracking based subgraph matching algorithms. In recent years, many advanced techniques for query vertex ordering (i.e., matching order generation) have been proposed to reduce the unpromising intermediate results according to the preset heuristic rules. In this paper, for the first time we apply the Reinforcement Learning (RL) and Graph Neural Networks (GNNs) techniques to generate the high-quality matching order for subgraph matching algorithms. Instead of using the fixed heuristics to generate the matching order, our model could capture and make full use of the graph information, and thus determine the query vertex order with the adaptive learning-based rule that could significantly reduces the number of redundant enumerations. With the help of the reinforcement learning framework, our model is able to consider the long-term benefits rather than only consider the local information at current ordering step.Extensive experiments on six real-life data graphs demonstrate that our proposed matching order generation technique could reduce up to two orders of magnitude of query processing time compared to the state-of-the-art algorithms.

Dynamic scheduling is an important problem in applications from queuing to wireless networks. It addresses how to choose an item among multiple scheduling items in each timestep to achieve a long-term goal. Conventional approaches for dynamic scheduling find the optimal policy for a given specific system so that the policy from these approaches is usable only for the corresponding system characteristics. Hence, it is hard to use such approaches for a practical system in which system characteristics dynamically change. This paper proposes a novel policy structure for MDP-based dynamic scheduling, a descriptive policy, which has a system-agnostic capability to adapt to unseen system characteristics for an identical task (dynamic scheduling). To this end, the descriptive policy learns a system-agnostic scheduling principle--in a nutshell, "which condition of items should have a higher priority in scheduling". The scheduling principle can be applied to any system so that the descriptive policy learned in one system can be used for another system. Experiments with simple explanatory and realistic application scenarios demonstrate that it enables system-agnostic meta-learning with very little performance degradation compared with the system-specific conventional policies.

As the rapid development of Artifical Intelligence in the current technology field, Reinforcement Learning has been proven as a powerful technique that allows autonomous agents to learn optimal behaviors (called policies) in unknown and complex environments through models of rewards and penalization. However, in order to make this technique (Reinforcement Learning) work correctly and get the precise reward function, which returns the feedback to the learning agent about when the agent behaves correctly or not, the reward function needs to be thoroughly specified. As a result, in real-world complex environments, such as autonomous driving, specifying a correct reward function could be one of the hard tasks to tackle for the Reinforcement Learning model designers. To this end, Apprenticeship Learning techniques, in which the agent can infer a reward function from expert behaviors, are of high interest due to the fact that they could result in highly specified reward function efficiently. However, for critical tasks such as autonomous driving, we need to critically consider about the safety-related issues, so as to we need to build techniques to automatically check and ensure that the inferred rewards functions and policies resulted from the Reinforcement Learning model fulfill the needed safety requirements of the critical tasks that we have mentioned previously. In order to have a well-designed Reinforcement Learning model, which is able to generate the highly-specified reward function satisfying the safety-related considerations, the technique called "Safety-Aware Apprenticeship Learning" was built in 2018[23], which would be introduced in detail in the later sections. Although the technique "Safety-Aware Apprenticeship Learning" has been built, it only considers Single-Agent scenario. In the other word, the current "Safety-Aware Apprenticeship Learning" technique can only be applied to one agent running in an isolated environment, a fact which limits the potential implementation of this technique.

The ability to learn reward functions plays an important role in enabling the deployment of intelligent agents in the real world. However, comparing reward functions, for example as a means of evaluating reward learning methods, presents a challenge. Reward functions are typically compared by considering the behavior of optimized policies, but this approach conflates deficiencies in the reward function with those of the policy search algorithm used to optimize it. To address this challenge, Gleave et al. (2020) propose the Equivalent-Policy Invariant Comparison (EPIC) distance. EPIC avoids policy optimization, but in doing so requires computing reward values at transitions that may be impossible under the system dynamics. This is problematic for learned reward functions because it entails evaluating them outside of their training distribution, resulting in inaccurate reward values that we show can render EPIC ineffective at comparing rewards. To address this problem, we propose the Dynamics-Aware Reward Distance (DARD), a new reward pseudometric. DARD uses an approximate transition model of the environment to transform reward functions into a form that allows for comparisons that are invariant to reward shaping while only evaluating reward functions on transitions close to their training distribution. Experiments in simulated physical domains demonstrate that DARD enables reliable reward comparisons without policy optimization and is significantly more predictive than baseline methods of downstream policy performance when dealing with learned reward functions.

State-of-the-art approaches to ObjectGoal navigation Prior work has made good progress on this task by rely on reinforcement learning and typically require significant formulating it as a reinforcement learning (RL) problem computational resources and time for learning. We and developing useful representations [20, 60], auxiliary propose Potential functions for ObjectGoal Navigation with tasks [61], data augmentation techniques [37], and improved Interaction-free learning (PONI), a modular approach that reward functions [37]. Despite this progress, end-toend disentangles the skills of'where to look?' for an object and RL incurs high computational cost, has poor sample efficiency, 'how to navigate to (x, y)?'. Our key insight is that'where and tends to generalize poorly to new scenes [7,12, to look?' can be treated purely as a perception problem, 37] since skills like moving without collisions, exploration, and learned without environment interactions. To address and stopping near the object are all learned from scratch this, we propose a network that predicts two complementary purely using RL. Modular navigation methods aim to address potential functions conditioned on a semantic map and uses these issues by disentangling'where to look for an object?' them to decide where to look for an unseen object. We train and'how to navigate to (x, y)?' [12,36]. These methods the potential function network using supervised learning on have emerged as strong competitors to end-to-end RL a passive dataset of top-down semantic maps, and integrate with good sample efficiency, better generalization to new it into a modular framework to perform ObjectGoal navigation.

Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the breadth, it is desirable to restrict the agent's attention at each step to a reasonable number of possible choices. The concept of affordances (Gibson, 1977) suggests that only certain actions are feasible in certain states. In this work, we model "affordances" through an attention mechanism that limits the available choices of temporally extended options. We present an online, model-free algorithm to learn affordances that can be used to further learn subgoal options. We investigate the role of hard versus soft attention in training data collection, abstract value learning in long-horizon tasks, and handling a growing number of choices. We identify and empirically illustrate the settings in which the paradox of choice arises, i.e. when having fewer but more meaningful choices improves the learning speed and performance of a reinforcement learning agent.