research
∙
07/07/2023
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Reinforcement learning (RL) algorithms face two distinct challenges: lea...
share
research
∙
06/15/2023
Block-State Transformer
State space models (SSMs) have shown impressive results on tasks that re...
research
∙
06/07/2023
Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design
In recent years, in-silico molecular design has received much attention ...
research
∙
09/13/2022
Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization
The ability to accelerate the design of biological sequences can have a ...
research
∙
05/16/2022
The Primacy Bias in Deep Reinforcement Learning
This work identifies a common flaw of deep reinforcement learning (RL) a...
research
∙
03/02/2022
Continuous-Time Meta-Learning with Forward Mode Differentiation
Drawing inspiration from gradient-based meta-learning methods with infin...
research
∙
02/22/2022
Myriad: a real-world testbed to bridge trajectory optimization and deep learning
We present Myriad, a testbed written in JAX for learning and planning in...
research
∙
12/22/2021
Direct Behavior Specification via Constrained Reinforcement Learning
The standard formulation of Reinforcement Learning lacks a practical way...
research
∙
10/11/2021
Neural Algorithmic Reasoners are Implicit Planners
Implicit planning has emerged as an elegant technique for combining lear...
research
∙
06/06/2021
Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation
The shortcomings of maximum likelihood estimation in the context of mode...
research
∙
03/10/2021
An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning
How do we formalize the challenge of credit assignment in reinforcement ...
research
∙
10/25/2020
XLVIN: eXecuted Latent Value Iteration Nets
Value Iteration Networks (VINs) have emerged as a popular method to inco...
research
∙
09/26/2020
Graph neural induction of value iteration
Many reinforcement learning tasks can benefit from explicit planning bas...
research
∙
07/06/2020
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
We investigate whether Jacobi preconditioning, accounting for the bootst...
research
∙
02/26/2020
Policy Evaluation Networks
Many reinforcement learning algorithms use value functions to guide the ...
research
∙
01/01/2020
Options of Interest: Temporal Abstraction with Interest Functions
Temporal abstraction refers to the ability of an agent to use behaviours...
research
∙
12/11/2019
Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
The policy gradient theorem is defined based on an objective with respec...
research
∙
10/21/2019
All-Action Policy Gradient Methods: A Numerical Integration Approach
While often stated as an instance of the likelihood ratio trick [Rubinst...
research
∙
10/15/2019
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
We establish a connection between the importance sampling estimators typ...
research
∙
11/16/2018
The Barbados 2018 List of Open Issues in Continual Learning
We want to make progress toward artificial general intelligence, namely ...
research
∙
02/09/2018
Learning Robust Options
Robust reinforcement learning aims to produce policies that have strong ...
research
∙
11/30/2017
Learnings Options End-to-End for Continuous Action Tasks
We present new results on learning temporally extended actions for conti...
research
∙
11/10/2017
Learning with Options that Terminate Off-Policy
A temporally abstract action, or an option, is specified by a policy and...
research
∙
09/14/2017
When Waiting is not an Option : Learning Options with a Deliberation Cost
Recent work has shown that temporally extended actions (options) can be ...
research
∙
05/25/2017
Convergent Tree-Backup and Retrace with Function Approximation
Off-policy learning is key to scaling up reinforcement learning as it al...
research
∙
12/03/2016
A Matrix Splitting Perspective on Planning with Options
We show that the Bellman operator underlying the options framework leads...
research
∙
09/16/2016