360 citations · 2.7k across the 150 of their papers we have counts for
24 papers · 1 filter
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi +2
A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action space…
Towards Continual Reinforcement Learning: A Review and Perspectives
Khimya Khetarpal, Matthew Riemer, Irina Rish +1
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary R…
A Study of Policy Gradient on a Class of Exactly Solvable Models
Gavin McCracken, Colin Daniels, Rosie Zhao +3
Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a…
Reward Propagation Using Graph Convolutional Networks
Martin Klissarov, Doina Precup
Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential function…
Gradient Starvation: A Learning Proclivity in Neural Networks
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio +3
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-…
Diversity-Enriched Option-Critic
Anand Kamat, Doina Precup
Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales. The option-critic framework has been demonst…