Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functions, are unknown a priori but the transition kernel is known. Such a setting is well-motivated by a number of applications including exploration of unknown, potentially unsafe, environments. We present an algorithm C-UCRL and show that it achieves sub-linear regret ($ O(T^{\frac{3}{4}}\sqrt{\log(T/\delta)})$) with respect to the reward while satisfying the constraints even while learning with probability $1-\delta$. Illustrative examples are provided.

How can societies learn to enforce and comply with social norms? Here we investigate the learning dynamics and emergence of compliance and enforcement of social norms in a foraging game, implemented in a multi-agent reinforcement learning setting. In this spatiotemporally extended game, individuals are incentivized to implement complex berry-foraging policies and punish transgressions against social taboos covering specific berry types. We show that agents benefit when eating poisonous berries is taboo, meaning the behavior is punished by other agents, as this helps overcome a credit-assignment problem in discovering delayed health effects. Critically, however, we also show that introducing an additional taboo, which results in punishment for eating a harmless berry, improves the rate and stability with which agents learn to punish taboo violations and comply with taboos. Counterintuitively, our results show that an arbitrary taboo (a "silly rule") can enhance social learning dynamics and achieve better outcomes in the middle stages of learning. We discuss the results in the context of studying normativity as a group-level emergent phenomenon.

The Complete Intelligence Global Cognitive System (GCS) was developed using Basic AI in 2015, and subsequently moved to a ML environment in 2016. In 2018, we expanded our analytic processes to harness the power of Deep Learning. At present, we are moving forward into the area of Reinforcement Learning to further improve our predictive efficiency. We begin our analytics with one of the world's largest global trade models that looks at more than 1,400 different industries and over 100 reporting countries. This is combined with thousands of commodities, equity indices, currencies and economic indicators to create a comprehensive model.

An online resource scheduling framework is proposed for minimizing the sum of weighted task latency for all the mobile users, by optimizing offloading decision, transmission power, and resource allocation in the mobile edge computing (MEC) system. Towards this end, a deep reinforcement learning (DRL) method is proposed to obtain an online resource scheduling policy. Firstly, a related and regularized stacked auto encoder (2r-SAE) with unsupervised learning is proposed to perform data compression and representation for high dimensional channel quality information (CQI) data, which can reduce the state space for DRL. Secondly, we present an adaptive simulated annealing based approach (ASA) as the action search method of DRL, in which an adaptive h-mutation is used to guide the search direction and an adaptive iteration is proposed to enhance the search efficiency during the DRL process. Thirdly, a preserved and prioritized experience replay (2p-ER) is introduced to assist the DRL to train the policy network and find the optimal offloading policy. Numerical results are provided to demonstrate that the proposed algorithm can achieve near-optimal performance while significantly decreasing the computational time compared with existing benchmarks. It also shows that the proposed framework is suitable for resource scheduling problem in large-scale MEC networks, especially in the dynamic environment.

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcement learning to learn how to take the next action so that the expected final level quality is maximized. This approach can be used when few or no examples exist to train from, and the trained generator is very fast. We investigate three different ways of transforming two-dimensional level design problems into Markov decision processes and apply these to three game environments.

Companies ranging from high tech startups to global multinationals see artificial intelligence as a key competitive advantage in an increasingly competitive and technical market. But, the AI industry moves so quickly that it's often hard to follow the latest research breakthroughs and achievements, and even harder to apply scientific results to achieve business outcomes. To help you develop a robust AI strategy for your business in 2020, I've summarized the latest trends across different research areas, including natural language processing, conversational AI, computer vision, and reinforcement learning. I've also included external education you can follow to further your expertise. In 2018, pre-trained language models pushed the limits of natural language understanding and generation. These also dominated NLP progress last year.

In this paper, a MIMO simulated annealing SA based Q learning method is proposed to control a line follower robot. The conventional controller for these types of robots is the proportional P controller. Considering the unknown mechanical characteristics of the robot and uncertainties such as friction and slippery surfaces, system modeling and controller designing can be extremely challenging. The mathematical modeling for the robot is presented in this paper, and a simulator is designed based on this model. The basic Q learning methods are based pure exploitation and the epsilon-greedy methods, which help exploration, can harm the controller performance after learning completion by exploring nonoptimal actions. The simulated annealing based Q learning method tackles this drawback by decreasing the exploration rate when the learning increases. The simulation and experimental results are provided to evaluate the effectiveness of the proposed controller.

This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the player to interact with the game using text. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents. Moreover, they provide a learning environment in which these skills can be acquired through interactions with an environment rather than using fixed corpora. One aspect that makes these games particularly challenging for learning agents is the combinatorially large action space. Existing methods for solving text-based games are limited to games that are either very simple or have an action space restricted to a predetermined set of admissible actions. In this work, we propose to use the exploration approach of Go-Explore for solving text-based games. More specifically, in an initial exploration phase, we first extract trajectories with high rewards, after which we train a policy to solve the game by imitating these trajectories. Our experiments show that this approach outperforms existing solutions in solving text-based games, and it is more sample efficient in terms of the number of interactions with the environment. Moreover, we show that the learned policy can generalize better than existing solutions to unseen games without using any restriction on the action space.

Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space. We contend that the dual uses of the knowledge graph to reason about game state and to constrain natural language generation are the keys to scalable exploration of combinatorially large natural language actions. Results across a wide variety of IF games show that KG-A2C outperforms current IF agents despite the exponential increase in action space size.

Constructing and maintaining knowledge of the world is a central problem for artificial intelligence research. Approaches to constructing an agent's knowledge using predictions have received increased amounts of interest in recent years. A particularly promising collection of research centres itself around architectures that formulate predictions as General Value Functions (GVFs), an approach commonly referred to as \textit{predictive knowledge}. A pernicious challenge for predictive knowledge architectures is determining what to predict. In this paper, we argue that evaluation methods---i.e., return error and RUPEE---are not well suited for the challenges of determining what to predict. As a primary contribution, we provide extended examples that evaluate predictions in terms of how they are used in further prediction tasks: a key motivation of predictive knowledge systems. We demonstrate that simply because a GVF's error is low, it does not necessarily follow the prediction is useful as a cumulant. We suggest evaluating 1) the relevance of a GVF's features to the prediction task at hand, and 2) evaluation of GVFs by \textit{how} they are used. To determine feature relevance, we generalize AutoStep to GTD, producing a step-size learning method suited to the life-long continual learning settings that predictive knowledge architectures are commonly deployed in. This paper contributes a first look into evaluation of predictions through their use, an integral component of predictive knowledge which is as of yet explored.