Search Results for author:
Found 9 papers, 5 papers with code
SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge
Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge".
Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach
By resorting to a neuro-symbolic approach, DERRL combines relational representations and constraints from symbolic planning with deep learning to extract interpretable policies.
EgoTV: Egocentric Task Verification from Natural Language Task Descriptions
The goal in EgoTV is to verify the execution of tasks from egocentric videos based on the natural language description of these tasks.
Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols
Human language has been described as a system that makes \textit{use of finite means to express an unlimited array of thoughts}.
gComm: An environment for investigating generalization in Grounded Language Acquisition
It comprises a 2-d grid environment with a set of agents (a stationary speaker and a mobile listener connected via a communication channel) exposed to a continuous array of tasks in a partially observable setting.
Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation
We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by an absolute percentage reduction of $\approx\mathbf{3-25\%}$ on multiple NLP tasks while achieving the same performance with no additional computation overhead.
Intrinsically Motivated Compositional Language Emergence
To deal with this, existing works have proposed a limited channel capacity as an important constraint for learning highly compositional languages.
Networked Multi-Agent Reinforcement Learning with Emergent Communication
One way to coordinate is by learning to communicate with each other.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation
We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by $\approx \mathbf{3-25\%}$ on an absolute scale on multiple NLP tasks while achieving the same performance with virtually no additional computation overhead.
