360 citations · 2.7k across the 150 of their papers we have counts for
15 papers · 2 filters
Marginalized State Distribution Entropy Regularization in Policy Optimization
Riashat Islam, Zafarali Ahmed, Doina Precup
Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid prem…
Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning
Riashat Islam, Raihan Seraj, Samin Yeasar Arnob +1
We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy…
Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
Riashat Islam, Raihan Seraj, Pierre-Luc Bacon +1
The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal…
Hindsight Credit Assignment
Anna Harutyunyan, Will Dabney, Thomas Mesnard +8
We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit…
Actor Critic with Differentially Private Critic
Jonathan Lebensold, William Hamilton, Borja Balle +1
Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-train…
Augmenting learning using symmetry in a biologically-inspired domain
Shruti Mishra, Abbas Abdolmaleki, Arthur Guez +2
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimension…
Avoidance Learning Using Observational Reinforcement Learning
David Venuto, Leonard Boussioux, Junhao Wang +4
Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous be…
Revisit Policy Optimization in Matrix Form
Sitao Luan, Xiao-Wen Chang, Doina Precup
In tabular case, when the reward and environment dynamics are known, policy evaluation can be written as , where is t…
Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning
Srinivas Venkattaramanujam, Eric Crawford, Thang Doan +1
Goal-conditioned policies are used in order to break down complex reinforcement learning (RL) problems by using subgoals, which can be defined either in state space or in a latent…
Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia
Charles C. Onu, Jonathan Lebensold, William L. Hamilton +1
Despite continuing medical advances, the rate of newborn morbidity and mortality globally remains high, with over 6 million casualties every year. The prediction of pathologies aff…
SVRG for Policy Evaluation with Fewer Gradient Evaluations
Zilun Peng, Ahmed Touati, Pascal Vincent +1
Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown t…
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
Sitao Luan, Mingde Zhao, Xiao-Wen Chang +1
Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. However, their bottlenecks still need to be a…
Recurrent Value Functions
Pierre Thodoroff, Nishanth Anand, Lucas Caccia +2
Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous con…
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
Mingde Zhao, Sitao Luan, Ian Porada +2
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well…
Learning Modular Safe Policies in the Bandit Setting with Application to Adaptive Clinical Trials
Hossein Aboutalebi, Doina Precup, Tibor Schuster
The stochastic multi-armed bandit problem is a well-known model for studying the exploration-exploitation trade-off. It has significant possible applications in adaptive clinical t…