Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence

no code implementations • 27 Jan 2023 • Lingwei Zhu, Zheng Chen, Matthew Schlegel, Martha White

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly.

Atari Games reinforcement-learning +1

Continual Auxiliary Task Learning

no code implementations • NeurIPS 2021 • Matthew McLeod, Chunlok Lo, Matthew Schlegel, Andrew Jacobsen, Raksha Kumaraswamy, Martha White, Adam White

Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems.

reinforcement-learning Reinforcement Learning (RL)

Structural Credit Assignment in Neural Networks using Reinforcement Learning

no code implementations • NeurIPS 2021 • Dhawal Gupta, Gabor Mihucz, Matthew Schlegel, James Kostas, Philip S. Thomas, Martha White

In this work, we revisit this approach and investigate if we can leverage other reinforcement learning approaches to improve learning.

reinforcement-learning Reinforcement Learning (RL)

Meta-descent for Online, Continual Prediction

no code implementations • 17 Jul 2019 • Andrew Jacobsen, Matthew Schlegel, Cameron Linke, Thomas Degris, Adam White, Martha White

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems.

Second-order methods Time Series +1

Importance Resampling for Off-policy Prediction

2 code implementations • NeurIPS 2019 • Matthew Schlegel, Wesley Chung, Daniel Graves, Jian Qian, Martha White

Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning.

Context-Dependent Upper-Confidence Bounds for Directed Exploration

no code implementations • NeurIPS 2018 • Raksha Kumaraswamy, Matthew Schlegel, Adam White, Martha White

Directed exploration strategies for reinforcement learning are critical for learning an optimal policy in a minimal number of interactions with the environment.

Efficient Exploration

Importance Resampling for Off-policy Policy Evaluation

no code implementations • 27 Sep 2018 • Matthew Schlegel, Wesley Chung, Daniel Graves, Martha White

We propose Importance Resampling (IR) for off-policy learning, that resamples experience from the replay buffer and applies a standard on-policy update.

General Value Function Networks

no code implementations • 18 Jul 2018 • Matthew Schlegel, Andrew Jacobsen, Zaheer Abbas, Andrew Patterson, Adam White, Martha White

A general purpose strategy for state construction is to learn the state update using a Recurrent Neural Network (RNN), which updates the internal state using the current internal state and the most recent observation.

Continuous Control Decision Making

Discovery of Predictive Representations With a Network of General Value Functions

no code implementations • ICLR 2018 • Matthew Schlegel, Andrew Patterson, Adam White, Martha White

We investigate a framework for discovery: curating a large collection of predictions, which are used to construct the agent's representation of the world.

Decision Making

Adapting Kernel Representations Online Using Submodular Maximization

no code implementations • ICML 2017 • Matthew Schlegel, Yangchen Pan, Jiecao Chen, Martha White

In this work, we develop an approximately submodular criterion for this setting, and an efficient online greedy submodular maximization algorithm for optimizing the criterion.

Continual Learning