Picture for Cheston Tan

Cheston Tan

FedHQL: Federated Heterogeneous Q-Learning

Jan 26, 2023
Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Cheston Tan, Bryan Kian Hsiang Low, Roger Wattenhofer

Figure 1 for FedHQL: Federated Heterogeneous Q-Learning

Figure 2 for FedHQL: Federated Heterogeneous Q-Learning

Figure 3 for FedHQL: Federated Heterogeneous Q-Learning

Figure 4 for FedHQL: Federated Heterogeneous Q-Learning

* Preprint. Under review

Access Paper or Ask Questions

Abductive Action Inference

Oct 24, 2022
Clement Tan, Chai Kiat Yeo, Cheston Tan, Basura Fernando

Figure 1 for Abductive Action Inference

Figure 2 for Abductive Action Inference

Figure 3 for Abductive Action Inference

Figure 4 for Abductive Action Inference

* 9 pages, 5 figures

Access Paper or Ask Questions

BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios

Jun 21, 2022
Jiafei Duan, Samson Yu, Nicholas Tan, Li Yi, Cheston Tan

Figure 1 for BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios

Figure 2 for BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios

Figure 3 for BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios

Figure 4 for BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios

* 9 pages, 5 figures

Access Paper or Ask Questions

Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

Jun 20, 2022
Jenny Zhang, Samson Yu, Jiafei Duan, Cheston Tan

Figure 1 for Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

Figure 2 for Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

Figure 3 for Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

Figure 4 for Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

* 11 Pages, 3 Figures

Access Paper or Ask Questions

ABCDE: An Agent-Based Cognitive Development Environment

Jun 10, 2022
Jieyi Ye, Jiafei Duan, Samson Yu, Bihan Wen, Cheston Tan

Figure 1 for ABCDE: An Agent-Based Cognitive Development Environment

Figure 2 for ABCDE: An Agent-Based Cognitive Development Environment

* Accepted to CVPRW 2022,Embodied AI Workshop (Extended Abstract)

Access Paper or Ask Questions

A Survey on Machine Learning Approaches for Modelling Intuitive Physics

Feb 14, 2022
Jiafei Duan, Arijit Dasgupta, Jason Fischer, Cheston Tan

Figure 1 for A Survey on Machine Learning Approaches for Modelling Intuitive Physics

Figure 2 for A Survey on Machine Learning Approaches for Modelling Intuitive Physics

Figure 3 for A Survey on Machine Learning Approaches for Modelling Intuitive Physics

* 9 Pages, 2 Figures

Access Paper or Ask Questions

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Nov 16, 2021
Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr, Yi Lin, Su-hua Wang, Renée Baillargeon, Cheston Tan

Figure 1 for A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Figure 2 for A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Figure 3 for A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Figure 4 for A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

* arXiv admin note: text overlap with arXiv:2110.05836

Access Paper or Ask Questions

Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Oct 26, 2021
Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan, Bryan Kian Hsiang Low

Figure 1 for Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Figure 2 for Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Figure 3 for Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Figure 4 for Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

* Accepted to 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Extended version with proofs and additional experimental details and results, 27 pages

Access Paper or Ask Questions