21 citations · 53 across the 8 of their papers we have counts for
9 papers
The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning
Andrew Patterson, Samuel Neumann, Raksha Kumaraswamy +2
This paper introduces a new empirical methodology, the Cross-environment Hyperparameter Setting Benchmark, that compares RL algorithms across environments using a single hyperparam…
Investigating the Interplay of Prioritized Replay and Generalization
Parham Mohammad Panahi, Andrew Patterson, Martha White +1
Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to…
When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
Vincent Liu, Prabhat Nagarajan, Andrew Patterson +1
Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is l…
Empirical Design in Reinforcement Learning
Andrew Patterson, Samuel Neumann, Martha White +1
Empirical design in reinforcement learning is no small task. Running good experiments requires attention to detail and at times significant computational resources. While compute r…
Robust Losses for Learning Value Functions
Andrew Patterson, Victor Liao, Martha White
Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outl…
A Temporal-Difference Approach to Policy Gradient Estimation
Samuele Tosatto, Andrew Patterson, Martha White +1
The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algor…
Online Off-policy Prediction
Sina Ghiassian, Andrew Patterson, Martha White +2
This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agen…
General Value Function Networks
Matthew Schlegel, Andrew Jacobsen, Zaheer Abbas +3
State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent…
Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains
Yangchen Pan, Muhammad Zaheer, Adam White +2
Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one…