
"It's Unwieldy and It Takes a Lot of Time." Challenges and Opportunities for Creating Agents in Commercial Games
Game agents such as opponents, nonplayer characters, and teammates are ...
read it

Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control
We address the problem of learning reusable state representations from s...
read it

Guaranteeing Reproducibility in Deep Learning Competitions
To encourage the development of methods with reproducible and robust tra...
read it

Recognizing Spatial Configurations of Objects with Graph Neural Networks
Deep learning algorithms can be seen as compositions of functions acting...
read it

Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learning
A major challenge in the Deep RL (DRL) community is to train agents able...
read it

Automatic Curriculum Learning For Deep RL: A Short Survey
Automatic Curriculum Learning (ACL) has become a cornerstone of recent s...
read it

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
The ability for policies to generalize to new environments is key to the...
read it

Better Exploration with Optimistic ActorCritic
Actorcritic methods, a type of modelfree Reinforcement Learning, have ...
read it

Variational Integrator Networks for Physically Meaningful Embeddings
Learning workable representations of dynamical systems is becoming an in...
read it

VariBAD: A Very Good Method for BayesAdaptive Deep RL via MetaLearning
Trading off exploration and exploitation in an unknown environment is ke...
read it

Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
We consider the problem of how a teacher algorithm can enable an unknown...
read it

Combining Noregret and Qlearning
Counterfactual Regret Minimization (CFR) has found success in settings l...
read it

NearOptimal Online Egalitarian learning in General Sum Repeated Matrix Games
We study twoplayer general sum repeated finite games where the rewards ...
read it

The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
Though deep reinforcement learning has led to breakthroughs in many diff...
read it

The MultiAgent Reinforcement Learning in MalmÖ (MARLÖ) Competition
Learning in multiagent scenarios is a fruitful research direction, but ...
read it

Successor Uncertainties: exploration and uncertainty in temporal difference learning
We consider the problem of balancing exploration and exploitation in seq...
read it

CAML: Fast Context Adaptation via MetaLearning
We propose CAML, a metalearning method for fast adaptation that partiti...
read it

Depth and nonlinearity induce implicit exploration for RL
The question of how to explore, i.e., take actions with uncertain outcom...
read it

Variational Inference for DataEfficient Model Learning in POMDPs
Partially observable Markov decision processes (POMDPs) are a powerful a...
read it

Cross Domain Regularization for Neural Ranking Models Using Adversarial Learning
Unlike traditional learning to rank models that depend on handcrafted f...
read it

Meta Reinforcement Learning with Latent Variable Gaussian Processes
Data efficiency, i.e., learning from small data sets, is critical in man...
read it

The Atari Grand Challenge Dataset
Recent progress in Reinforcement Learning (RL), fueled by its combinatio...
read it

A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
Reinforcement learning is concerned with identifying rewardmaximizing b...
read it

Memory Lens: How Much Memory Does an Agent Use?
We propose a new method to study the internal memory used by reinforceme...
read it

Experimental and causal view on information integration in autonomous agents
The amount of digitally available but heterogeneous information about th...
read it
Katja Hofmann
verfied profile