Advances in neural information processing systems 2
Using probabilistic knowledge and simulation to play poker
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
World-championship-caliber Scrabble
Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning words from sights and sounds: a computational model
Learning words from sights and sounds: a computational model
Grounding knowledge in sensors: unsupervised learning for language and planning
Grounding knowledge in sensors: unsupervised learning for language and planning
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
On the role of tracking in stationary environments
Proceedings of the 24th international conference on Machine learning
Learning to sportscast: a test of grounded language acquisition
Proceedings of the 25th international conference on Machine learning
Sample-based learning and search with permanent and transient memories
Proceedings of the 25th international conference on Machine learning
An Analysis of UCT in Multi-player Games
CG '08 Proceedings of the 6th international conference on Computers and Games
On the integration of grounding language and learning objects
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Grounding the lexical semantics of verbs in visual perception using force dynamics and event logic
Journal of Artificial Intelligence Research
UCT for tactical assault planning in real-time strategy games
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Reinforcement learning for mapping instructions to actions
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Learning semantic correspondences with less supervision
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Learning context-dependent mappings from sentences to logical form
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Reading to learn: constructing features from semantic abstracts
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Intentional context in situated natural language learning
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
Learning to follow navigational directions
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Reading between the lines: learning to map high-level instructions to commands
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Driving semantic parsing from the world's response
CoNLL '10 Proceedings of the Fourteenth Conference on Computational Natural Language Learning
Learning to win by reading manuals in a Monte-Carlo framework
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Learning dependency-based compositional semantics
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Confidence driven unsupervised semantic parsing
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Non-linear Monte-Carlo search in civilization II
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Hi-index | 0.00 |
Domain knowledge is crucial for effective performance in autonomous control systems. Typically, human effort is required to encode this knowledge into a control algorithm. In this paper, we present an approach to language grounding which automatically interprets text in the context of a complex control application, such as a game, and uses domain knowledge extracted from the text to improve control performance. Both text analysis and control strategies are learned jointly using only a feedback signal inherent to the application. To effectively leverage textual information, our method automatically extracts the text segment most relevant to the current game state, and labels it with a task-centric predicate structure. This labeled text is then used to bias an action selection policy for the game, guiding it towards promising regions of the action space. We encode our model for text analysis and game playing in a multi-layer neural network, representing linguistic decisions via latent variables in the hidden layers, and game action quality via the output layer. Operating within the Monte-Carlo Search framework, we estimate model parameters using feedback from simulated games. We apply our approach to the complex strategy game Civilization II using the official game manual as the text guide. Our results show that a linguistically-informed game-playing agent significantly outperforms its language-unaware counterpart, yielding a 34% absolute improvement and winning over 65% of games when playing against the built-in AI of Civilization.