ServiceNow AI Research

Reinforcement Learning

LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
In Reinforcement Learning (RL), an agent is guided by the rewards it receives from the reward function. Unfortunately, it may take many …
International Join Conference on Artificial Intelligence (IJCAI),  2018.
PDF Cite Code
Teaching Multiple Tasks to an RL Agent using LTL
Teaching Multiple Tasks to an RL Agent using LTL
This paper examines the problem of how to teach multiple tasks to a Reinforcement Learning (RL) agent. To this end, we use Linear …
Autonomous Agents and Multiagent Systems (AAMAS),  2018.
PDF Cite
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning
In this paper we propose Reward Machines – a type of finite state machine that supports the spec- ification of reward functions while …
International Conference on Machine Learning (ICML),  2018.
PDF Cite Code
Advice-Based Exploration in Model-Based Reinforcement Learning
Advice-Based Exploration in Model-Based Reinforcement Learning
Convergence to an optimal policy using model-based rein- forcement learning can require significant exploration of the environment. In …
Canadian Conference on AI,  2018.
PDF Cite
LLMs can learn self-restraint through iterative self-reflection
LLMs can learn self-restraint through iterative self-reflection
In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their …
Transactions on Machine Learning Research (TMLR),  2017.
PDF Cite Video