research
∙
08/21/2023
Stabilizing Unsupervised Environment Design with a Learned Adversary
A key challenge in training generally-capable agents is the design of tr...
share
research
∙
03/12/2023
Synthetic Experience Replay
A key theme in the past decade has been that when large neural networks ...
research
∙
03/06/2023
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Open-ended learning methods that automatically generate a curriculum of ...
research
∙
01/18/2023
Human-Timescale Adaptation in an Open-Ended Task Space
Foundation models have shown impressive adaptation and scalability in su...
research
∙
11/29/2022
The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning
We study the use of model-based reinforcement learning methods, in parti...
research
∙
10/23/2022
Learning General World Models in a Handful of Reward-Free Deployments
Building generally capable agents is a grand challenge for deep reinforc...
research
∙
07/23/2022
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Practising and honing skills forms a fundamental component of how humans...
research
∙
07/19/2022
Bayesian Generational Population-Based Training
Reinforcement learning (RL) offers the potential for training generally ...
research
∙
07/11/2022
Grounding Aleatoric Uncertainty in Unsupervised Environment Design
Adaptive curricula in reinforcement learning (RL) have proven effective ...
research
∙
06/09/2022
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Offline reinforcement learning has shown great promise in leveraging lar...
research
∙
03/22/2022
Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 N...
research
∙
03/08/2022
On-the-fly Strategy Adaptation for ad-hoc Agent Coordination
Training agents in cooperative settings offers the promise of AI agents ...
research
∙
03/02/2022
Evolving Curricula with Regret-Based Environment Design
It remains a significant challenge to train generally capable agents wit...
research
∙
01/11/2022
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
The combination of Reinforcement Learning (RL) with deep learning has le...
research
∙
12/24/2021
Lyapunov Exponents for Diversity in Differentiable Games
Ridge Rider (RR) is an algorithm for finding diverse solutions to optimi...
research
∙
11/04/2021
Towards an Understanding of Default Policies in Multitask Policy Optimization
Much of the recent success of deep reinforcement learning has been drive...
research
∙
10/08/2021
Revisiting Design Choices in Model-Based Offline Reinforcement Learning
Offline reinforcement learning enables agents to leverage large pre-coll...
research
∙
10/06/2021
Replay-Guided Adversarial Environment Design
Deep reinforcement learning (RL) agents may successfully generalize to n...
research
∙
09/27/2021
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
The progress in deep reinforcement learning (RL) is heavily driven by th...
research
∙
07/16/2021
Graph Kernel Attention Transformers
We introduce a new class of graph neural networks (GNNs), by combining s...
research
∙
06/30/2021
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
Despite a series of recent successes in reinforcement learning (RL), man...
research
∙
06/05/2021
Same State, Different Task: Continual Reinforcement Learning without Interference
Continual Learning (CL) considers the problem of training an agent seque...
research
∙
04/12/2021
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Reinforcement learning from large-scale offline datasets provides us wit...
research
∙
02/08/2021
Unlocking Pixels for Reinforcement Learning via Implicit Attention
There has recently been significant interest in training reinforcement l...
research
∙
02/07/2021
Deep Reinforcement Learning with Dynamic Optimism
In recent years, deep off-policy actor-critic algorithms have become a d...
research
∙
01/19/2021
ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning
We introduce ES-ENAS, a simple neural architecture search (NAS) algorith...
research
∙
11/12/2020
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
Over the last decade, a single algorithm has changed many facets of our ...
research
∙
06/21/2020
On Optimism in Model-Based Reinforcement Learning
The principle of optimism in the face of uncertainty is prevalent throug...
research
∙
03/30/2020
Stochastic Flows and Geometric Optimization on the Orthogonal Group
We present a new class of stochastic, geometrically-driven optimization ...
research
∙
02/07/2020
Ready Policy One: World Building Through Active Learning
Model-Based Reinforcement Learning (MBRL) offers a promising direction f...
research
∙
02/06/2020
One-Shot Bayes Opt with Probabilistic Population Based Training
Selecting optimal hyperparameters is a key challenge in machine learning...
research
∙
02/03/2020
Effective Diversity in Population-Based Reinforcement Learning
Maintaining a population of solutions has been shown to increase explora...
research
∙
07/10/2019
Reinforcement Learning with Chromatic Networks
We present a new algorithm for finding compact neural networks encoding ...
research
∙
06/11/2019
Wasserstein Reinforcement Learning
We propose behavior-driven optimization via Wasserstein distances (WDs) ...
research
∙
05/29/2019
Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
We propose a new class of structured methods for Monte Carlo (MC) sampli...
research
∙
03/07/2019
Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces
We present a new algorithm ASEBO for conducting optimization of high-dim...
research
∙
03/07/2019