Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative offline RL algorithms struggle to generalize to unseen actions, despite their success in learning good in-distribution policy. In contrast, we propose to use the gradient fields of the dataset density generated from a pre-trained offline RL algorithm to adjust the original actions. We decouple the conservatism constraints from the policy, thus can benefit wide offline RL algorithms. As a consequence, we propose the Conservative Denoising Score-based Algorithm (CDSA) which utilizes the denoising score-based model to model the gradient of the dataset density, rather than the dataset density itself, and facilitates a more accurate and efficient method to adjust the action generated by the pre-trained policy in a deterministic and continuous MDP environment. In experiments, we show that our approach significantly improves the performance of baseline algorithms in D4RL datasets, and demonstrate the generalizability and plug-and-play capability of our model across different pre-trained offline RL policy in different tasks. We also validate that the agent exhibits greater risk aversion after employing our method while showcasing its ability to generalize effectively across diverse tasks.

The Indian Institute of Management, Ahmedabad, has announced the launch of the Brij Disa Centre for Data Science and Artificial Intelligence (CDSA). This specialised centre will undertake cutting-edge research in data science and AI to support businesses, governance, and policymaking. It also aims at building collaborative relationships between scholars and practitioners along with conducting case-based research to understand the current industry practice. The centre will also be developing case studies for classroom teaching. The endowment for CDSA has been contributed by Dipak Gupta, joint managing director, Kotak Mahindra Group, an alumnus of IIMA.

The Indian Institute of Management (IIM) Ahmedabad today launched the Brij Disa Centre for Data Science and Artificial Intelligence (CDSA). The centre shall undertake leading-edge research in data science and artificial intelligence that will support businesses, governance, and policymaking. It aims to forge synergistic and collaborative relationships between scholars and practitioners in data-intensive organisations, besides undertaking case-based research to understand the current industry practice and develop case studies for classroom teaching. The endowment for this centre has been contributed by Deepak Gupta, joint managing director, Kotak Mahindra Group. Errol D'Souza, director, IIM Ahmedabad, said, "Data Science and artificial intelligence are increasingly impacting businesses across the world. AI has become an inevitable part of our lives. To harness the power of these advanced technologies for augmenting businesses, the need of the hour is to bring together different stakeholders onto the same platform, conduct intensive research to identify challenges, determine potential and provide impactful insights."

The Indian Institute of Management (IIM) Ahmedabad has launched the Brij Disa Centre for Data Science and Artificial Intelligence (CDSA) to enable research in the field. This will support businesses, governance, and policymaking, the institute states. It aims to connect scholars and practitioners in data-intensive organisations. It will also undertake case-based research to understand the current industry practice and develop case studies for classroom teaching. CDSA will also be responsible for the dissemination of the knowledge to a wide audience both within and outside the realm of the institute through seminars, workshops, and conferences.

Indian Institute of Management (IIM) Ahmedabad has launched the'Brij Disa Centre for Data Science and Artificial Intelligence (CDSA)', the institute said on Monday. The endowment for the centre has been contributed by Deepak Gupta, Joint Managing Director, Kotak Mahindra Group, it said. The centre will undertake research in Data Science and Artificial Intelligence to support businesses, governance, and policymaking. The centre aims for synergistic and collaborative relationships between scholars and practitioners in data-intensive organizations, besides undertaking case-based research to understand the current industry practice and develop case studies for classroom teaching, an official statement said. Besides connecting relevant stakeholders, CDSA will also be responsible for "dissemination of the knowledge to a wide audience both within and outside the realm of the Institute through seminars, workshops and conferences," it added.

Many real-world applications involve multivariate, geo-tagged time series data: at each location, multiple sensors record corresponding measurements. For example, air quality monitoring system records PM2.5, CO, etc. The resulting time-series data often has missing values due to device outages or communication errors. In order to impute the missing values, state-of-the-art methods are built on Recurrent Neural Networks (RNN), which process each time stamp sequentially, prohibiting the direct modeling of the relationship between distant time stamps. Recently, the self-attention mechanism has been proposed for sequence modeling tasks such as machine translation, significantly outperforming RNN because the relationship between each two time stamps can be modeled explicitly. In this paper, we are the first to adapt the self-attention mechanism for multivariate, geo-tagged time series data. In order to jointly capture the self-attention across multiple dimensions, including time, location and the sensor measurements, while maintain low computational complexity, we propose a novel approach called Cross-Dimensional Self-Attention (CDSA) to process each dimension sequentially, yet in an order-independent manner. Our extensive experiments on four real-world datasets, including three standard benchmarks and our newly collected NYC-traffic dataset, demonstrate that our approach outperforms the state-of-the-art imputation and forecasting methods. A detailed systematic analysis confirms the effectiveness of our design choices.