An actor-critic agent that restricts its actions to recipe-guided high-level commands and learned navigation generalizes to unseen games in a cooking-themed text-based game family, scoring 69.3% on the challenge test set.
What can you do with a rock? Affordance extraction via word embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Autonomous agents must often detect affordances: the set of behaviors enabled by a situation. Affordance detection is particularly helpful in domains with large action spaces, allowing the agent to prune its search space by avoiding futile behaviors. This paper presents a method for affordance extraction via word embeddings trained on a Wikipedia corpus. The resulting word vectors are treated as a common knowledge database which can be queried using linear algebra. We apply this method to a reinforcement learning agent in a text-only environment and show that affordance-based action selection improves performance most of the time. Our method increases the computational complexity of each learning step but significantly reduces the total number of steps needed. In addition, the agent's action selections begin to resemble those a human would choose.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games
An actor-critic agent that restricts its actions to recipe-guided high-level commands and learned navigation generalizes to unseen games in a cooking-themed text-based game family, scoring 69.3% on the challenge test set.