More Like this

1. Agent goal management using goal operations

   Kondrakunta, Sravya; Gogineni, Venkatsampath R.; Cox, Michael T. (November 2021, Proceedings of the 9th Goal Reasoning Workshop)

   Goal management in autonomous agents has been a problem of interest for a long time. Multiple goal operations are required to solve an agent goal management problem. For example, some goal operations include selection, change, formulation, delegation, monitoring. Many researchers from different fields developed several solution approaches with an implicit or explicit focus on goal operations. For example, some solution approaches include scheduling the agents’ goals, performing cost-benefit analysis to select/organize goals, agent goal formulation in unexpected situations. However, none of them explicitly shed light on the agents’ response when multiple goal operations occur simultaneously. This paper develops an algorithm to address agent goal management when multiple-goal operations co-occur and presents how such an interaction would improve agent goal management in different domains. 

   more » « less
2. Goal-Oriented Script Construction

   Lyu, Qing; Zhang, Li; Callison-Burch Chris (January 2021, Proceedings of the 14th International Conference on Natural Language Generation)

   The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance. 

   more » « less
3. Multi-agent goal delegation

   Gogineni, Venkatsampath R.; Kondrakunta, Sravya; Cox, Michael T. (November 2021, Proceedings of the 9th Goal Reasoning Workshop)

   Autonomous agents in a multi-agent system work with each other to achieve their goals. However, In a partially observable world, current multi-agent systems are often less effective in achieving their goals. This limitation is due to the agents’ lack of reasoning about other agents and their mental states. Another factor is the agents’ inability to share required knowledge with other agents. This paper addresses the limitations by presenting a general approach for autonomous agents to work together in a multi-agent system. In this approach, an agent applies two main concepts: goal reasoning- to determine what goals to pursue and share; Theory of mind-to select an agent(s) for sharing goals and knowledge. We evaluate the performance of our multi-agent system in a Marine Life Survey Domain and compare it to another multi-agent system that randomly selects agent(s) to delegates its goals. 

   more » « less
4. Goal orientations of general chemistry students via the achievement goal framework

   https://doi.org/10.1039/C7RP00148G  

   Lewis, Scott E. (January 2018, Chemistry Education Research and Practice)

   null (Ed.)

   The Achievement Goal Framework describes students’ goal orientations as: task-based, focusing on the successful completion of the task; self-based, evaluating performance relative to one's own past performance; or other-based, evaluating performance relative to the performance of others. Goal orientations have been used to explain student success in a range of educational settings, but have not been used in post-secondary chemistry. This study describes the goal orientations of General Chemistry students and explores the relationship of goal orientations to success in the course. On average, students report higher task and self orientations than other orientation. Task orientation had a positive relationship with exam performance and self orientation had a negative relationship with exam performance. Clustering students showed that for the majority of students task and self orientations moved concurrently and students with low preference across the three orientations also performed lowest on exams. Finally, students in classes using Flipped-Peer Led Team Learning, a pedagogy designed to bring active learning to a large lecture class, showed higher task orientation than those in classes with lecture-based instruction. 

   more » « less
5. Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

   Torne, Marcel; Balsells, Max; Wang, Zihan; Desai, Samedh; Chen, Tao; Agrawal, Pulkit; Gupta, Abhishek (December 2023, Neural Information Processing Systems 2023)

   Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration requires either careful design of reward functions or the use of novelty-seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we present a technique called Human Guided Exploration (HuGE), which uses low-quality feedback from non-expert users that may be sporadic, asynchronous, and noisy. HuGE guides exploration for reinforcement learning not only in simulation but also in the real world, all without meticulous reward specification. The key concept involves bifurcating human feedback and policy learning: human feedback steers exploration, while self-supervised learning from the exploration data yields unbiased policies. This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses. HuGE is able to learn a variety of challenging multi-stage robotic navigation and manipulation tasks in simulation using crowdsourced feedback from non-expert users. Moreover, this paradigm can be scaled to learning directly on real-world robots, using occasional, asynchronous feedback from human supervisors. 

   more » « less