Corpus ID: 209386673

Learning Generalizable Visual Representations via Interactive Gameplay

@article{Weihs2019LearningGV,
  title={Learning Generalizable Visual Representations via Interactive Gameplay},
  author={Luca Weihs and Aniruddha Kembhavi and Kiana Ehsani and Sarah Pratt and Winson Han and Alvaro Herrasti and Eric Kolve and Dustin Schwenk and R. Mottaghi and A. Farhadi},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.08195}
}
A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in developing the neural flexibility for creative problem solving, decision making, and socialization. Comparatively little is known regarding the impact of embodied gameplay upon artificial agents. While recent work has produced agents proficient in abstract games, these environments are far removed from the real world… Expand
AllenAct: A Framework for Embodied AI Research
Visual Perspective Taking for Opponent Behavior Modeling
Audio-Visual Embodied Navigation
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

References

SHOWING 1-10 OF 63 REFERENCES
Visual Hide and Seek
Human-level control through deep reinforcement learning
Children and robots learning to play hide and seek
Mastering the game of Go without human knowledge
Curiosity-Driven Exploration by Self-Supervised Prediction
Hindsight Experience Replay
The Developmental Progression of Understanding of Mind during a Hiding Game.
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Games and the Development of Perspective Taking
Juvenile play experience primes neurons in the medial prefrontal cortex to be more responsive to later experiences
...
1
2
3
4
5
...