Search Results for author:
Found 6 papers, 4 papers with code
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines.
Offline Multitask Representation Learning for Reinforcement Learning
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation.
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings.
Randomized Exploration for Reinforcement Learning with General Value Function Approximation
We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle.
Path-Based Contextualization of Knowledge Graphs for Textual Entailment
In this paper, we introduce the problem of knowledge graph contextualization -- that is, given a specific NLP task, the problem of extracting meaningful and relevant sub-graphs from a given knowledge graph.
TVAE: Triplet-Based Variational Autoencoder using Metric Learning
Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning.
