Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expertise at the world's oldest board games and many classic video games, but they require vast quantities of experience to learn successfully -- none of today's algorithms account for the human ability to learn so many different tasks, so quickly. Here we propose a new approach to this challenge based on a particularly strong form of model-based RL which we call Theory-Based Reinforcement Learning, because it uses human-like intuitive theories -- rich, abstract, causal models of physical objects, intentional agents, and their interactions -- to explore and model an environment, and plan effectively to achieve task goals. We instantiate the approach in a video game playing agent called EMPA (the Exploring, Modeling, and Planning Agent), which performs Bayesian inference to learn probabilistic generative models expressed as programs for a game-engine simulator, and runs internal simulations over these models to support efficient object-based, relational exploration and heuristic planning. EMPA closely matches human learning efficiency on a suite of 90 challenging Atari-style video games, learning new games in just minutes of game play and generalizing robustly to new game situations and new levels. The model also captures fine-grained structure in people's exploration trajectories and learning dynamics. Its design and behavior suggest a way forward for building more general human-like AI systems.

Playtesting is an essential step in the game design process. Game designers use the feedback from playtests to refine their design. Game designers may employ procedural personas to automate the playtesting process. In this paper, we present two approaches to improve automated playtesting. First, we propose a goal-based persona model, which we call developing persona -- developing persona proposes a dynamic persona model, whereas the current persona models are static. Game designers can use the developing persona to model the changes that a player undergoes while playing a game. Additionally, a human playtester knows which paths she has tested before, and during the consequent tests, she may test different paths. However, RL agents disregard the previously generated trajectories. We propose a novel methodology that helps Reinforcement Learning (RL) agents to generate distinct trajectories than the previous trajectories. We refer to this methodology as Alternative Path Finder (APF). We present a generic APF framework that can be applied to all RL agents. APF is trained with the previous trajectories, and APF distinguishes the novel states from similar states. We use the General Video Game Artificial Intelligence (GVG-AI) and VizDoom frameworks to test our proposed methodologies. We use Proximal Policy Optimization (PPO) RL agent during experiments. First, we show that the playtest data generated by the developing persona cannot be generated using the procedural personas. Second, we present the alternative paths found using APF. We show that the APF penalizes the previous paths and rewards the distinct paths.

Artificial Intelligence (AI) has had the power of ruling the technologically dominated world for quite some time now. Today, we have reached a stage wherein advanced artificial intelligence has become one of the most sought after techniques to bring about innovation and solve complex business problems. Over the last few years, the technology has matured to the extent that it has become highly scalable. In the midst of all this, what has grabbed eyeballs from everywhere across is reinforcement learning – training the machine learning models to be able to make the best possible decisions. Reinforcement learning makes use of algorithms that do not rely only on historical data sets, to learn to make a prediction or perform a task.

Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings. Imitation Learning (IL) can learn from expert demonstrations without exploration, but it never exceeds the expert's performance and is also vulnerable to distributional shift between demonstration and execution. In this paper, we radically unify RL and IL based on Free Energy Principle (FEP). FEP is a unified Bayesian theory of the brain that explains perception, action and model learning by a common fundamental principle. We present a theoretical extension of FEP and derive an algorithm in which an agent learns the world model that internalizes expert demonstrations and at the same time uses the model to infer the current and future states and actions that maximize rewards. The algorithm thus reduces exploration costs by partially imitating experts as well as maximizing its return in a seamless way, resulting in a higher performance than the suboptimal expert. Our experimental results show that this approach is promising in visual control tasks especially in sparse-reward environments.

How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving. Training with simulated data is less costly and dangerous than utilizing real-world data, but the inconsistency of parameter distribution and the incorrect system modeling in simulators always lead to an inevitable Sim2real gap, which probably accounts for the underperformance in novel, anomalous and risky cases that simulators can hardly generate. Domain Randomization(DR) is a methodology that can bridge this gap with little or no real-world data. Consequently, in this research, an adversarial model is put forward to robustify DeepRL-based autonomous vehicles trained in simulation to gradually surfacing harder events, so that the models could readily transfer to the real world.

Cooperative multi-agent systems are being widely used in variety of areas. Interaction between agents would bring positive points, including reducing costs of operating, high scalability, and facilitating parallel processing. These systems pave the way for handling large-scale, unknown, and dynamic environments. However, learning in these environments has become a prominent challenge in different applications. These challenges include the effect of size of search space on learning time, inappropriate cooperation among agents, and the lack of proper coordination among agents' decisions. Moreover, reinforcement learning algorithms may suffer from long time of convergence in these problems. In this paper, a communication framework using knowledge transfer concepts is introduced to address such challenges in the herding problem with large state space. To handle the problems of convergence, knowledge transfer has been utilized that can significantly increase the efficiency of reinforcement learning algorithms. Coordination between the agents is carried out through a head agent in each group of agents and a coordinator agent respectively. The results demonstrate that this framework could indeed enhance the speed of learning and reduce convergence time.

When agents are swarmed to carry out a mission, there is often a sudden failure of some of the agents observed from the command base. It is generally difficult to distinguish whether the failure is caused by actuators (hypothesis, $h_a$) or sensors (hypothesis, $h_s$) solely by the communication between the command base and the concerning agent. By making a collision to the agent by another, we would be able to distinguish which hypothesis is likely: For $h_a$, we expect to detect corresponding displacements while for $h_a$ we do not. Such swarm strategies to grasp the situation are preferably to be generated autonomously by artificial intelligence (AI). Preferable actions ($e.g.$, the collision) for the distinction would be those maximizing the difference between the expected behaviors for each hypothesis, as a value function. Such actions exist, however, only very sparsely in the whole possibilities, for which the conventional search based on gradient methods does not make sense. Instead, we have successfully applied the reinforcement learning technique, achieving the maximization of such a sparse value function. The machine learning actually concluded autonomously the colliding action to distinguish the hypothesises. Getting recognized an agent with actuator error by the action, the agents behave as if other ones want to assist the malfunctioning one to achieve a given mission.

For oil and gas companies looking at drilling wells in a new field, the issue becomes one of return vs. cost. The goal is simple enough: install the fewest number of wells that will draw them the most oil or gas from the underground reservoirs for the longest amount of time. The more wells installed, the higher the cost and the larger the impact on the environment. However, finding the right well placements quickly becomes a highly complex math problem. Too few wells sited in the wrong places leaves a lot of resources in the ground.

We present Bayesian Controller Fusion (BCF): a hybrid control strategy that combines the strengths of traditional hand-crafted controllers and model-free deep reinforcement learning (RL). BCF thrives in the robotics domain, where reliable but suboptimal control priors exist for many tasks, but RL from scratch remains unsafe and data-inefficient. By fusing uncertainty-aware distributional outputs from each system, BCF arbitrates control between them, exploiting their respective strengths. We study BCF on two real-world robotics tasks involving navigation in a vast and long-horizon environment, and a complex reaching task that involves manipulability maximisation. For both these domains, there exist simple handcrafted controllers that can solve the task at hand in a risk-averse manner but do not necessarily exhibit the optimal solution given limitations in analytical modelling, controller miscalibration and task variation.

Modeling the dynamics of epidemics helps to propose control strategies based on pharmaceuticaland non-pharmaceutical interventions (contact limitation, lockdown, vaccination,etc). Hand-designing such strategies is not trivial because of the number of possibleinterventions and the difficulty to predict long-term effects. This task can be cast as an optimization problem where state-of-the-art machine learning methods such as deep reinforcement learning might bring significant value. However, the specificity of each domain|epidemic modeling or solving optimization problems|requires strong collaborationsbetween researchers from different fields of expertise. This is why we introduce EpidemiOptim, a Python toolbox that facilitates collaborations between researchers inepidemiology and optimization. EpidemiOptim turns epidemiological models and cost functions into optimization problems via a standard interface commonly used by optimization practitioners (OpenAI Gym). Reinforcement learning algorithms based on QLearning with deep neural networks (DQN) and evolutionary algorithms (NSGA-II) are already implemented. We illustrate the use of EpidemiOptim to find optimal policies fordynamical on-o  lockdown control under the optimization of the death toll and economic recess using a Susceptible-Exposed-Infectious-Removed (SEIR) model for COVID-19. Using EpidemiOptim and its interactive visualization platform in Jupyter notebooks, epidemiologists, optimization practitioners and others (e.g. economists) can easily compare epidemiological models, costs functions and optimization algorithms to address important choicesto be made by health decision-makers. Trained models can be explored by experts and non-experts via a web interface. This article is part of the special track on AI and COVID-19.