Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. This problem motivated many research directions on embodied language use. Current approaches focus on language as a communication tool in very simplified and non diverse social situations: the "naturalness" of language is reduced to the concept of high vocabulary size and variability. In this paper, we argue that aiming towards human-level AI requires a broader set of key social skills: 1) language use in complex and variable social contexts; 2) beyond language, complex embodied communication in multimodal settings within constantly evolving social worlds. In this work we explain how concepts from cognitive sciences could help AI to draw a roadmap towards human-like intelligence, with a focus on its social dimensions. We then study the limits of a recent SOTA Deep RL approach when tested on a first grid-world environment from the upcoming SocialAI, a benchmark to assess the social skills of Deep RL agents. Videos and code are available at https://sites.google.com/view/socialai01 .

Animation is a big bottleneck in all game development. Characters or creatures have to be designed and scripted manually, to achieve seemingly realistic interactions with the world. That makes it hard to achieve scale without growing your game team. So over the past two years, we've continued down the path of physical animation based on reinforcement learning. In short, that means we train physically-based machines to walk by giving them rewards for doing the right things -- like virtual dog treats.

From cutting costs to improving customer experience, forecasting is the crux of retail supply chain management (SCM) and the key to better supply chain performance. Several retailers are using AI/ML models to gather datasets and provide forecast guidance in applications such as Cognitive Demand Forecasting, Product End-of-Life, Forecasting, and Demand Integrated Product Flow. Early work in these areas looked at classical algorithms to improve on a gamut of challenges such as network flow and graphs. But the recent disruptions have made it critical for supply chains to have the resiliency to handle unexpected events. The biggest challenge lies in matching supply with demand. Reinforcement Learning (RL) with its ability to train systems to respond to unforeseen environments, is being increasingly adopted in SCM to improve forecast accuracy, solve supply chain optimization challenges, and train systems to respond to unforeseen circumstances. Companies like UPS and Amazon have developed RL algorithms to define winning AI strategies and keep up with rising consumer delivery expectations. While there are many ways to build RL algorithms for supply chain use cases, the OpenAI Gym toolkit is becoming the preferred choice because of the robust framework for event-driven simulations. This white paper explores the application of RL in supply chain forecasting and describes how to build suitable RL models and algorithms by using the OpenAI Gym toolkit.

We test the performance of deep deterministic policy gradient (DDPG), a deep reinforcement learning algorithm, able to handle continuous state and action spaces, to learn Nash equilibria in a setting where firms compete in prices. These algorithms are typically considered model-free because they do not require transition probability functions (as in e.g., Markov games) or predefined functional forms. Despite being model-free, a large set of parameters are utilized in various steps of the algorithm. These are e.g., learning rates, memory buffers, state-space dimensioning, normalizations, or noise decay rates and the purpose of this work is to systematically test the effect of these parameter configurations on convergence to the analytically derived Bertrand equilibrium. We find parameter choices that can reach convergence rates of up to 99%. The reliable convergence may make the method a useful tool to study strategic behavior of firms even in more complex settings. Keywords: Bertrand Equilibrium, Competition in Uniform Price Auctions, Deep Deterministic Policy Gradient Algorithm, Parameter Sensitivity Analysis

State-of-the-art human-in-the-loop robot grasping is hugely suffered by Electromyography (EMG) inference robustness issues. As a workaround, researchers have been looking into integrating EMG with other signals, often in an ad hoc manner. In this paper, we are presenting a method for end-to-end training of a policy for human-in-the-loop robot grasping on real reaching trajectories. For this purpose we use Reinforcement Learning (RL) and Imitation Learning (IL) in DEXTRON (DEXTerity enviRONment), a stochastic simulation environment with real human trajectories that are augmented and selected using a Monte Carlo (MC) simulation method. We also offer a success model which once trained on the expert policy data and the RL policy roll-out transitions, can provide transparency to how the deep policy works and when it is probably going to fail.

Created by Lazy Programmer Team, Lazy Programmer Inc.Preview this Course - GET COUPON CODE Have you ever thought about what would happen if you combined the power of machine learning and artificial intelligence with financial engineering? Today, you can stop imagining, and start doing. This course will teach you the core fundamentals of financial engineering, with a machine learning twist. We will cover must-know topics in financial engineering, such as: Exploratory data analysis, significance testing, correlations, alpha and beta Time series analysis, simple moving average, exponentially-weighted moving average Holt-Winters exponential smoothing model Efficient Market Hypothesis Random Walk Hypothesis Time series forecasting ("stock price prediction") Modern portfolio theory Efficient frontier / Markowitz bullet Mean-variance optimization Maximizing the Sharpe ratio Convex optimization with Linear Programming and Quadratic Programming Capital Asset Pricing Model (CAPM) Algorithmic trading (VIP only) Statistical Factor Models (VIP only) Regime Detection with Hidden Markov Models (VIP only) In addition, we will look at various non-traditional techniques which stem purely from the field of machine learning and artificial intelligence, such as: Classification models Unsupervised learning Reinforcement learning and Q-learning ***VIP-only sections (get it while it lasts!) You will learn exactly why their methodology is fundamentally flawed and why their results are complete nonsense.

We consider a meal delivery service fulfilling dynamic customer requests given a set of couriers over the course of a day. A courier's duty is to pick-up an order from a restaurant and deliver it to a customer. We model this service as a Markov decision process and use deep reinforcement learning as the solution approach. We experiment with the resulting policies on synthetic and real-world datasets and compare those with the baseline policies. We also examine the courier utilization for different numbers of couriers. In our analysis, we specifically focus on the impact of the limited available resources in the meal delivery problem. Furthermore, we investigate the effect of intelligent order rejection and re-positioning of the couriers. Our numerical experiments show that, by incorporating the geographical locations of the restaurants, customers, and the depot, our model significantly improves the overall service quality as characterized by the expected total reward and the delivery times. Our results present valuable insights on both the courier assignment process and the optimal number of couriers for different order frequencies on a given day. The proposed model also shows a robust performance under a variety of scenarios for real-world implementation.

Reinforcement Learning (RL) agents have great successes in solving tasks with large observation and action spaces from limited feedback. Still, training the agents is data-intensive and there are no guarantees that the learned behavior is safe and does not violate rules of the environment, which has limitations for the practical deployment in real-world scenarios. This paper discusses the engineering of reliable agents via the integration of deep RL with constraint-based augmentation models to guide the RL agent towards safe behavior. Within the constraints set, the RL agent is free to adapt and explore, such that its effectiveness to solve the given problem is not hindered. However, once the RL agent leaves the space defined by the constraints, the outside models can provide guidance to still work reliably. We discuss integration points for constraint guidance within the RL process and perform experiments on two case studies: a strictly constrained card game and a grid world environment with additional combinatorial subgoals. Our results show that constraint-guidance does both provide reliability improvements and safer behavior, as well as accelerated training.

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, but the representation of the context determines the degree of generalization and expressivity. Categorical contexts preclude generalization to entirely new tasks. Goal-conditioned policies may enable some generalization, but cannot capture all tasks that might be desired. In this paper, we propose goal distributions as a general and broadly applicable task representation suitable for contextual policies. Goal distributions are general in the sense that they can represent any state-based reward function when equipped with an appropriate distribution class, while the particular choice of distribution class allows us to trade off expressivity and learnability. We develop an off-policy algorithm called distribution-conditioned reinforcement learning (DisCo RL) to efficiently learn these policies. We evaluate DisCo RL on a variety of robot manipulation tasks and find that it significantly outperforms prior methods on tasks that require generalization to new goal distributions.

This paper explores the use of reinforcement learning (RL) models for autonomous racing. In contrast to passenger cars, where safety is the top priority, a racing car aims to minimize the lap-time. We frame the problem as a reinforcement learning task with a multidimensional input consisting of the vehicle telemetry, and a continuous action space. To find out which RL methods better solve the problem and whether the obtained models generalize to driving on unknown tracks, we put 10 variants of deep deterministic policy gradient (DDPG) to race in two experiments: i)~studying how RL methods learn to drive a racing car and ii)~studying how the learning scenario influences the capability of the models to generalize. Our studies show that models trained with RL are not only able to drive faster than the baseline open source handcrafted bots but also generalize to unknown tracks.