research
∙
06/27/2023
Value-aware Importance Weighting for Off-policy Reinforcement Learning
Importance sampling is a central idea underlying off-policy prediction i...
share
research
∙
06/23/2023
Maintaining Plasticity in Deep Continual Learning
Modern deep-learning systems are specialized to problem settings in whic...
research
∙
09/30/2022
On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs
We show two average-reward off-policy control algorithms, Differential Q...
research
∙
08/23/2022
The Alberta Plan for AI Research
Herein we describe our approach to artificial intelligence research, whi...
research
∙
07/04/2022
Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Value iteration (VI) is a foundational dynamic programming method, impor...
research
∙
05/25/2022
Toward Discovering Options that Achieve Faster Planning
We propose a new objective for option discovery that emphasizes the comp...
research
∙
02/26/2022
The Quest for a Common Model of the Intelligent Decision Maker
The premise of Multi-disciplinary Conference on Reinforcement Learning a...
research
∙
02/20/2022
A History of Meta-gradient: Gradient Methods for Meta-learning
The history of meta-learning methods based on gradient descent is review...
research
∙
02/07/2022
Reward-Respecting Subtasks for Model-Based Reinforcement Learning
To achieve the ambitious goals of artificial intelligence, reinforcement...
research
∙
12/30/2021
Learning Agent State Online with Recurrent Generate-and-Test
Learning continually and online from a continuous stream of data is chal...
research
∙
10/26/2021
Average-Reward Learning and Planning with Options
We extend the options framework for temporal abstraction in reinforcemen...
research
∙
09/10/2021
An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment
Many off-policy prediction learning algorithms have been proposed in the...
research
∙
08/13/2021
Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
The Backprop algorithm for learning in neural networks utilizes two mech...
research
∙
06/02/2021
An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task
Off-policy prediction – learning the value function for one policy from ...
research
∙
04/17/2021
Planning with Expectation Models for Control
In model-based reinforcement learning (MBRL), Wan et al. (2019) showed c...
research
∙
02/15/2021
Does Standard Backpropagation Forget Less Catastrophically Than Adam?
Catastrophic forgetting remains a severe hindrance to the broad applicat...
research
∙
01/08/2021
Average-Reward Off-Policy Policy Evaluation with Function Approximation
We consider off-policy policy evaluation with function approximation (FA...
research
∙
10/28/2020
Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning
Despite empirical success, the theory of reinforcement learning (RL) wit...
research
∙
08/27/2020
Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
Intelligent assistants that follow commands or answer simple questions, ...
research
∙
08/26/2020
Inverse Policy Evaluation for Value-based Sequential Decision-making
Value-based methods for reinforcement learning lack generally applicable...
research
∙
06/29/2020
Learning and Planning in Average-Reward Markov Decision Processes
We introduce improved learning and planning algorithms for average-rewar...
research
∙
12/09/2019
Learning Sparse Representations Incrementally in Deep Reinforcement Learning
Sparse representations have been shown to be useful in deep reinforcemen...
research
∙
10/04/2019
Discounted Reinforcement Learning is Not an Optimization Problem
Discounted reinforcement learning is fundamentally incompatible with fun...
research
∙
09/09/2019
Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning
We explore fixed-horizon temporal difference (TD) methods, reinforcement...
research
∙
04/02/2019
Planning with Expectation Models
Distribution and sample models are two popular model choices in model-ba...
research
∙
03/08/2019
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning
There is a long history of using meta learning as representation learnin...
research
∙
03/01/2019
Should All Temporal Difference Learning Use Emphasis?
Emphatic Temporal Difference (ETD) learning has recently been proposed a...
research
∙
01/22/2019
Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
Multi-step methods such as Retrace(λ) and n-step Q-learning have become ...
research
∙
11/06/2018
Online Off-policy Prediction
This paper investigates the problem of online prediction learning, where...
research
∙
09/20/2018
Predicting Periodicity with Temporal Difference Learning
Temporal difference (TD) learning is an important approach in reinforcem...
research
∙
07/05/2018
Per-decision Multi-step Temporal Difference Learning with Control Variates
Multi-step temporal difference (TD) learning is an important approach in...
research
∙
06/01/2018
Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling
Episodic memory is a psychology term which refers to the ability to reca...
research
∙
05/18/2018
Two geometric input transformation methods for fast online reinforcement learning with neural nets
We apply neural nets with ReLU gates in online reinforcement learning. O...
research
∙
04/10/2018
TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent
In this paper, we introduce a method for adapting the step-sizes of temp...
research
∙
02/16/2018
Reactive Reinforcement Learning in Asynchronous Environments
The relationship between a reinforcement learning (RL) agent and an asyn...
research
∙
01/25/2018
Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods
This paper investigates estimating the variance of a temporal-difference...
research
∙
12/04/2017
A Deeper Look at Experience Replay
Experience replay plays an important role in the success of deep reinfor...
research
∙
11/10/2017
Communicative Capital for Prosthetic Agents
This work presents an overarching perspective on the role that machine i...
research
∙
05/11/2017
A First Empirical Study of Emphatic Temporal Difference Learning
In this paper we present the first empirical study of the emphatic tempo...
research
∙
05/09/2017
Integral Policy Iterations for Reinforcement Learning Problems in Continuous Time and Space
Policy iteration (PI) is a recursive process of policy evaluation and im...
research
∙
12/09/2016
Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks
Representations are fundamental to artificial intelligence. The performa...
research
∙
06/09/2016
Face valuing: Training user interfaces with facial expressions and reinforcement learning
An important application of interactive machine learning is extending or...
research
∙
12/13/2015
True Online Temporal-Difference Learning
The temporal-difference methods TD(λ) and Sarsa(λ) form a core part of m...
research
∙
07/01/2015
An Empirical Evaluation of True Online TD(λ)
The true online TD(λ) algorithm has recently been proposed (van Seijen a...
research
∙
09/18/2013
Temporal-Difference Learning to Assist Human Decision Making during the Control of an Artificial Limb
In this work we explore the use of reinforcement learning (RL) to help w...
research
∙
01/10/2013
Planning by Prioritized Sweeping with Small Backups
Efficient planning plays a crucial role in model-based reinforcement lea...
research
∙
06/13/2012