The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle out-of-support region. Model-based RL methods offer a richer dataset and benefit generalization by generating imaginary trajectories with either trained forward or reverse dynamics model. However, the imagined transitions may be inaccurate, thus downgrading the performance of the underlying offline RL method. In this paper, we propose to augment the offline dataset by using trained bidirectional dynamics models and rollout policies with double check. We introduce conservatism by trusting samples that the forward model and backward model agree on. Our method, confidence-aware bidirectional offline model-based imagination, generates reliable samples and can be combined with any model-free offline RL method. Experimental results on the D4RL benchmarks demonstrate that our method significantly boosts the performance of existing model-free offline RL algorithms and achieves competitive or better scores against baseline methods.

The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle out-of-support region. Model-based RL methods offer a richer dataset and benefit generalization by generating imaginary trajectories with either trained forward or reverse dynamics model. However, the imagined transitions may be inaccurate, thus downgrading the performance of the underlying offline RL method. In this paper, we propose to augment the offline dataset by using trained bidirectional dynamics models and rollout policies with double check. We introduce conservatism by trusting samples that the forward model and backward model agree on. Our method, confidence-aware bidirectional offline model-based imagination, generates reliable samples and can be combined with any model-free offline RL method.

Click here to see Forbes India's comprehensive coverage on the Covid-19 situation and its impact on life, business and the economy

Machine learning (ML) is currently disrupting almost every industry and is being used as the core component in many systems. The decisions made by these systems may have a great impact on society and specific individuals and thus the decision-making process has to be clear and explainable so humans can trust it. Explainable AI (XAI) is a rather new field in ML in which researchers try to develop models that are able to explain the decision-making process behind ML models. In this talk we'll learn about the fundamentals of XAI and discuss why we need to start to integrate XAI with our ML models!

More than seven out of every ten marketers are trusting just one technology to make sense of all their challenges in 2018. And it just might succeed ... if it doesn't also take their jobs. Or if privacy regulations reduce the amount of data available to power it. Artificial intelligence is set to be the most transformative technology in marketing in 2018, according to more than 345 CMOs, CEOs, and marketing experts I surveyed recently. This past year, marketers learned that they had too much data. Too much to understand, and too much data to react to.

Arisha Smith is business leaders and innovator. The Dallas resident is the principal and founder of Idyllic Interactive, an agency set to assist you in growing your business and make smarter data driven decisions. Read to learn how she got to the top. What inspires you to show at work everyday? Since I own my own business, it's the opportunity to create a legacy for my children.

The paper discusses the issue of trusting, or the active management of trust (Fitzhugh/etal:2011), in human-robot teams. The paper approaches the issue from the viewpoint of asymmetric agency, and social sentience. The assumption is that humans and robots experience reality differently (asymmetry), and that a robot is endowed with an explicit (deliberative) awareness of its role within the team, and of the social dynamics of the team (social sentience). A formal approach is outlined, to provide the basis for a model of trusting in terms of (i) trust in information and how to act upon that (as judgements about actions and interactions, at the task-level), and (ii) the reflection of trust between actors in a team, in how social dynamics get directed over time (team-level). The focus is thus primarily on the integration of trust and its adaptation in the dynamics of collaboration.