Skip to content. | Skip to navigation

Personal tools

Navigation

You are here: Home
21 items matching your search terms.
Filter the results.
Item type
















New items since



Sort by relevance · date (newest first) · alphabetically
Jongmin Lee
by Jongmin Lee published Apr 13, 2018
Located in People
Article Reference Layered Behavior Modeling via Combining Descriptive and Prescriptive Approaches: a Case Study of Infantry Company Engagement
by Jongmin Lee published May 02, 2018 last modified Mar 08, 2019 12:26 PM
Defense modeling and simulation (DM&S) has brought insights into how to efficiently operate combat entities, such as soldiers and weapon systems. Most DM&S works have been developed to reflect accurate descriptions of military doctrines, yet these doctrines provide only guidelines of military operations, not details about how the combat entities should behave. Because such vague parts are often fulfilled with the appropriate behavior of combat entities in a battlefield, one part argues that DM&S should consider individual combat behaviors as well. However, it is known as an infeasible problem discovering best individual actions from infinite searching space, such as the battlefield. This paper proposes a layered behavior modeling to practically resolve this issue. The proposed method applies descriptive modeling to reduce the searching space by employing domain-specific knowledge; and prescriptive modeling to discover best individual actions in the reduced space. For the generalization, the proposed method adapts both modeling methods being modularized, and then the proposed method suggested an interface between them that is based on their semantic analogies. Both modeling methods are modularized, so they are interacted through an interface defined in the proposed method. This paper presents a realization of the proposed method through a case study of infantry company-level operations. In the case study, the proposed method is implemented with discrete event system specification formalism as the descriptive part and Markov decision process as the prescriptive part. The experimental results illustrated that the combat effectiveness resulted from the proposed method is statistically better than that from the descriptive-only modeling, and the difference would be guided by the objective of the combat behavior. Through the presented experimental results and the discussion, this paper argues that future DM&S should consider a broad spectrum from the battlefield incorporating the rational behavior of military individuals.
Located in Papers
PDF File PDF document Hierarchical Bayesian Inverse Reinforcement Learning
by Jongmin Lee published May 02, 2018
PDF of Choi, J and Kim, K (2015): IEEE Transactions on Cybernetics, 45(4). Located at portal path: http://localhost:8080/aipr/papers/CK2015
Located in Papers / PDFs
Inproceedings Reference Octet Stream Monte-Carlo Tree Search for Constrained MDPs
by Jongmin Lee published Sep 07, 2018 last modified Mar 08, 2019 12:26 PM
Monte-Carlo Tree Search (MCTS) is the state-of-the-art online planning algorithm for very large MDPs. However, many real-world problems inherently have multiple goals, where multi-objective sequential decision models are more natural. The constrained MDP (CMDP) is such a model that maximizes the reward while constraining the cost. The common solution method for CMDPs is linear programming (LP), which is hardly applicable to large real-world problems. In this paper, we present CCUCT (Cost-Constrained UCT), an online planning algorithm for large constrained MDPs (CMDPs) that leverages the optimization of LP-induced parameters. We show that CCUCT converges to the optimal stochastic action selection in CMDPs and it is able to solve very large CMDPs through experiments on the multi-objective version of an Atari 2600 arcade game.
Located in Papers
PDF File PDF document Monte-Carlo Tree Search for Constrained MDPs
by Jongmin Lee published Sep 07, 2018 last modified Mar 08, 2019 12:26 PM
PDF of Lee, J, Kim, G, Poupart, P, and Kim, K (2018): In: ICML/IJCAI/AAMAS Workshop on Planning and Learning (PAL). Located at portal path: http://localhost:8080/aipr/papers/LKPK2018a
Located in Papers / PDFs
Inproceedings Reference Monte-Carlo Tree Search for Constrained POMDPs
by Jongmin Lee published Dec 27, 2018 last modified Jul 12, 2021 09:17 PM
Monte-Carlo Tree Search (MCTS) has been successfully applied to very large POMDPs, a standard model for stochastic sequential decision-making problems. However, many real-world problems inherently have multiple goals, where multi-objective formulations are more natural. The constrained POMDP (CPOMDP) is such a model that maximizes the reward while constraining the cost, extending the standard POMDP model. To date, solution methods for CPOMDPs assume an explicit model of the environment, and thus are hardly applicable to large-scale real-world problems. In this paper, we present CC-POMCP (Cost-Constrained POMCP), an online MCTS algorithm for large CPOMDPs that leverages the optimization of LP-induced parameters and only requires a black-box simulator of the environment. In the experiments, we demonstrate that CC-POMCP converges to the optimal stochastic action selection in CPOMDP and pushes the state-of-the-art by being able to scale to very large problems.
Located in Papers
PDF File PDF document Monte-Carlo Tree Search for Constrained POMDPs
by Jongmin Lee published Oct 02, 2018 last modified Jul 12, 2021 09:17 PM
PDF of Lee, J, Kim, G, Poupart, P, and Kim, K (2018): In: Proceedings of Neural Information Processing Systems (NeurIPS). Located at portal path: http://ailab.kaist.ac.kr/papers/LKPK2018
Located in Papers / PDFs
Conference Reference Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients
by Jongmin Lee published Nov 22, 2019 last modified Jul 12, 2021 09:16 PM
Monte-Carlo Tree Search (MCTS) is the state-of-the-art online planning algorithm for large problems with discrete action spaces. However, many real-world problems involve continuous action spaces, where MCTS is not as effective as in discrete action spaces. This is mainly due to common practices such as coarse discretization of the entire action space and failure to exploit local smoothness. In this paper, we introduce Value-Gradient UCT (VG-UCT), which combines traditional MCTS with gradient-based optimization of action particles. VG-UCT simultaneously performs a global search via UCT with respect to the finitely sampled set of actions and performs a local improvement via action value gradients. In the experiments, we demonstrate that our approach outperforms existing MCTS methods and other strong baseline algorithms for continuous action spaces.
Located in Papers
PDF File PDF document Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients
by Jongmin Lee published Nov 22, 2019 last modified Jul 12, 2021 09:16 PM
PDF of Lee, J, Jeon, W, Kim, G, and Kim, K (2020): In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). Located at portal path: http://ailab.kaist.ac.kr/papers/LJKK2020
Located in Papers / PDFs
PDF File PDF document End-to-End Neural Pipeline for Goal-Oriented Dialogue System using GPT-2
by Jongmin Lee published May 06, 2020 last modified Jul 01, 2020 01:10 AM
PDF of Ham*-, D, Lee*-, J, Jang, Y, and Kim, K (2020): In: AAAI Conference on Artificial Intelligence (AAAI) DSTC8 Workshop. Located at portal path: http://ailab.kaist.ac.kr/papers/HLJK2020_AAAI
Located in Papers / PDFs