Search Results for author:
Found 9 papers, 2 papers with code
In-Context Analogical Reasoning with Pre-Trained Language Models
Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences.
Composing Task Knowledge with Modular Successor Feature Approximators
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.
Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention
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.
Reinforcement Learning of Implicit and Explicit Control Flow in Instructions
Learning to flexibly follow task instructions in dynamic environments poses interesting challenges for reinforcement learning agents.
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment
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.
Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning
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.
Reward Mapping for Transfer in Long-Lived Agents
We demonstrate that our approach can substantially improve the agent's performance relative to other approaches, including an approach that transfers policies.
Reward Design via Online Gradient Ascent
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.
