ServiceNow Research

Reinforcement Learning

Beyond Target Networks: Improving Deep Q-learning with Functional Regularization
Beyond Target Networks: Improving Deep Q-learning with Functional Regularization
Target networks are at the core of recent success in Reinforcement Learning. They stabilize the training by using old parameters to …
Transactions on Machine Learning Research,  2022.
PDF Cite
Direct Behavior Specification via Constrained Reinforcement Learning
Direct Behavior Specification via Constrained Reinforcement Learning
The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors. …
International Conference on Machine Learning (ICML),  2022.
PDF Cite
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
Reinforcement learning (RL) aims at autonomously performing complex tasks. To this end, a reward signal is used to steer the learning …
Workshop at the International Conference on Machine Learning (ICML),  2022.
PDF Cite
Scaling up ML-based Black-box Planning with Partial STRIPS Models
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
ICAPS'22 Workshop on Reliable Data-Driven Planning and Scheduling,  2022.
PDF Cite Code
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
Reinforcement Learning via Supervised Learning (RvS) only uses supervised techniques to learn desirable behaviors from large datasets. …
Workshop at the International Conference on Learning Representations (ICLR),  2022.
PDF Cite Code
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
PDF Cite Code
Reinforcement Learning with Random Delays
Reinforcement Learning with Random Delays
Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study …
International Conference on Learning Representations (ICLR),  2021.
PDF Cite Code
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization
Combinatorial optimization has found applications in numerous fields, from aerospace to transportation planning and economics. The goal …
Association for the Advancement of Artificial Intelligence (AAAI),  2021.
PDF Cite Code
Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint …
Conference on Neural Information Processing Systems (NeurIPS),  2020.
PDF Cite
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
As deep reinforcement learning driven by visual perception becomes more widely used there is a growing need to better understand and …
International Conference on Learning Representations (ICLR),  2020.
PDF Cite