Search Results for author: Marina Dubova

Found 4 papers, 3 papers with code

One system for learning and remembering episodes and rules

1 code implementation8 Jul 2024 Joshua T. S. Hewson, Sabina J. Sloman, Marina Dubova

Humans can learn individual episodes and generalizable rules and also successfully retain both kinds of acquired knowledge over time.

Building Human-like Communicative Intelligence: A Grounded Perspective

no code implementations2 Jan 2022 Marina Dubova

After making astounding progress in language learning in the recent decade, AI systems, however, seem to approach the ceiling that does not reflect important aspects of human communicative capacities.

Common Sense Reasoning Image Classification

Reinforcement Communication Learning in Different Social Network Structures

1 code implementation ICML Workshop LaReL 2020 Marina Dubova, Arseny Moskvichev, Robert Goldstone

We examined the effects of social network organization on the properties of communication systems emerging in decentralized, multi-agent reinforcement learning communities.

Multi-agent Reinforcement Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.