Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Subbarao Kambhampati

Subbarao Kambhampati

Large Language Models Still Can't Plan (A Benchmark for LLMs on Planning and Reasoning about Change)

Jun 21, 2022
Karthik Valmeekam, Alberto Olmo, Sarath Sreedharan, Subbarao Kambhampati

Access Paper or Ask Questions

A Mental-Model Centric Landscape of Human-AI Symbiosis

Feb 18, 2022
Zahra Zahedi, Sarath Sreedharan, Subbarao Kambhampati

Figure 1 for A Mental-Model Centric Landscape of Human-AI Symbiosis

Figure 2 for A Mental-Model Centric Landscape of Human-AI Symbiosis

Figure 3 for A Mental-Model Centric Landscape of Human-AI Symbiosis

Figure 4 for A Mental-Model Centric Landscape of Human-AI Symbiosis

Access Paper or Ask Questions

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Feb 06, 2022
Lin Guan, Sarath Sreedharan, Subbarao Kambhampati

Figure 1 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Figure 2 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Figure 3 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Figure 4 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Access Paper or Ask Questions

Gradient-Based Mixed Planning with Discrete and Continuous Actions

Oct 19, 2021
Kebing Jin, Hankz Hankui Zhuo, Zhanhao Xiao, Hai Wan, Subbarao Kambhampati

Figure 1 for Gradient-Based Mixed Planning with Discrete and Continuous Actions

Figure 2 for Gradient-Based Mixed Planning with Discrete and Continuous Actions

Figure 3 for Gradient-Based Mixed Planning with Discrete and Continuous Actions

Figure 4 for Gradient-Based Mixed Planning with Discrete and Continuous Actions

* 36 pages, 20 figures

Access Paper or Ask Questions

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Oct 14, 2021
Yantian Zha, Lin Guan, Subbarao Kambhampati

Figure 1 for Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Figure 2 for Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Figure 3 for Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Access Paper or Ask Questions

Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems

Sep 21, 2021
Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma, Yantian Zha, Lin Guan

Figure 1 for Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems

Access Paper or Ask Questions

Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

Sep 20, 2021
Sriram Gopalakrishnan, Mudit Verma, Subbarao Kambhampati

Figure 1 for Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

Figure 2 for Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

Figure 3 for Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

Figure 4 for Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

* 7 page paper, 6 pages supplemental material

Access Paper or Ask Questions

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

Aug 09, 2021
Sriram Gopalakrishnan, Utkarsh Soni, Tung Thai, Panagiotis Lymperopoulos, Matthias Scheutz, Subbarao Kambhampati

Figure 1 for Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

Access Paper or Ask Questions

Not all users are the same: Providing personalized explanations for sequential decision making problems

Jun 23, 2021
Utkarsh Soni, Sarath Sreedharan, Subbarao Kambhampati

Figure 1 for Not all users are the same: Providing personalized explanations for sequential decision making problems

Figure 2 for Not all users are the same: Providing personalized explanations for sequential decision making problems

Figure 3 for Not all users are the same: Providing personalized explanations for sequential decision making problems

Access Paper or Ask Questions