1 code implementation • 28 May 2023 • Xiaoyang Hu, Shane Storks, Richard L. Lewis, Joyce Chai
Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences.
1 code implementation • 28 Jan 2023 • Wilka Carvalho, Angelos Filos, Richard L. Lewis, Honglak Lee, Satinder Singh
Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing, and transferring predictive knowledge and behavior.
no code implementations • NAACL (CMCL) 2021 • Soo Hyun Ryu, Richard L. Lewis
We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2.
no code implementations • 25 Feb 2021 • Ethan A. Brooks, Janarthanan Rajendran, Richard L. Lewis, Satinder Singh
Learning to flexibly follow task instructions in dynamic environments poses interesting challenges for reinforcement learning agents.
no code implementations • 28 Oct 2020 • Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L. Lewis, Satinder Singh
In this work, we show that one can learn object-interaction tasks from scratch without supervision by learning an attentive object-model as an auxiliary task during task learning with an object-centric relational RL agent.
no code implementations • NeurIPS 2014 • Xiaoxiao Guo, Satinder Singh, Honglak Lee, Richard L. Lewis, Xiaoshi Wang
The combination of modern Reinforcement Learning and Deep Learning approaches holds the promise of making significant progress on challenging applications requiring both rich perception and policy-selection.
no code implementations • NeurIPS 2013 • Xiaoxiao Guo, Satinder Singh, Richard L. Lewis
We demonstrate that our approach can substantially improve the agent's performance relative to other approaches, including an approach that transfers policies.
no code implementations • NeurIPS 2010 • Jonathan Sorg, Richard L. Lewis, Satinder P. Singh
In this work, we develop a gradient ascent approach with formal convergence guarantees for approximately solving the optimal reward problem online during an agent's lifetime.