Learning to Win Games in a Few Examples: Using Game-Theory and Demonstrations to Learn the Win Conditions of a Connect Four Game

Ayub, Ali; Wagner, Alan R.

doi:10.1007/978-3-030-05204-1_34

“…The multi-modal dialogues are structured as sequences of sub-dialogues, where each sub-dialogue starts with a visual demonstration of a game board showing a new way to win. The use of demonstrations of win conditions is based on observations from our previous work of how people start asking questions to learn a new game (Ayub and Wagner, 2018). As indicated below, each win condition corresponds to a path to a win state in an extensiveform game tree, where the opponent's game actions are left unspecified.…”

Section: Related Workmentioning

confidence: 99%

Dialogue Policies for Learning Board Games through Multimodal Communication

Zare,

Ayub,

Liu

et al. 2020

Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue

1

0

View full text Add to dashboard Cite

This paper presents MDP policy learning for agents to learn strategic behavior-how to play board games-during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialoguefinal knowledge state. During policy training, we control for the simulated dialogue partner's level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner's informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the system's language skills as above average. Further, results confirm that human dialogue partners also vary in their informativeness.

show abstract

“…The multi-modal dialogues are structured as sequences of sub-dialogues, where each sub-dialogue starts with a visual demonstration of a game board showing a new way to win. The use of demonstrations of win conditions is based on observations from our previous work of how people start asking questions to learn a new game (Ayub and Wagner, 2018). As indicated below, each win condition corresponds to a path to a win state in an extensiveform game tree, where the opponent's game actions are left unspecified.…”

Section: Related Workmentioning

confidence: 99%