• Publications
  • Influence
Unsupervised State Representation Learning in Atari
TLDR
This work introduces a method that learns state representations by maximizing mutual information across spatially and temporally distinct features of a neural encoder of the observations and introduces a new benchmark based on Atari 2600 games to evaluate representations based on how well they capture the ground truth state variables.
Data-Efficient Reinforcement Learning with Self-Predictive Representations
TLDR
The method, Self-Predictive Representations (SPR), trains an agent to predict its own latent state representations multiple steps into the future using an encoder which is an exponential moving average of the agent’s parameters and a learned transition model.
HoME: a Household Multimodal Environment
TLDR
HoME is an open-source, OpenAI Gym-compatible platform extensible to tasks in reinforcement learning, language grounding, sound-based navigation, robotics, multi-agent learning, and more that better enables artificial agents to learn as humans do: in an interactive, multimodal, and richly contextualized setting.
We Used Neural Networks to Detect Clickbaits: You Won't Believe What Happened Next!
TLDR
A neural network architecture based on Recurrent Neural Networks for detecting clickbaits is introduced, which relies on distributed word representations learned from a large unannotated corpora, and character embeddings learned via Convolutional Neural Networks.
Blindfold Baselines for Embodied QA
TLDR
It is shown through experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.
Pretraining Representations for Data-Efficient Reinforcement Learning
TLDR
This work uses unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data, and employs a combination of latent dynamics modelling and unsupervised goal-conditioned RL to encourage learning representations which capture diverse aspects of the underlying MDP.
Procedural Generalization by Planning with Self-Supervised World Models
TLDR
Overall, this work suggests that building generalizable agents requires moving beyond the single-task, model-free paradigm and towards self-supervised model-based agents that are trained in rich, procedural, multi-task environments.
Data-Efficient Reinforcement Learning with Momentum Predictive Representations
TLDR
This work trains an agent to predict its own latent state representations multiple steps into the future using an encoder which is an exponential moving average of the agent's parameters, and makes predictions using a learned transition model.
FairScholar: Balancing Relevance and Diversity for Scientific Paper Recommendation
TLDR
A novel scientific paper recommendation system that aims at balancing both relevance and diversity while searching for research papers in response to keyword queries, which performs a vertex reinforced random-walk on the citation graph of papers in order to factor in diversity while serving recommendations.
Contrastive Self-Supervised Learning
...
...