arXiv research

Bayesian model for multi-environment prediction with latent variable changes.

New method learns robust representations by modeling environment variation.

GALA framework learns invariant graph representations via environment augmentation with minimal assumptions.

Exploration in environments with continuous control and sparse rewards remains a key challenge in reinforcement learning (RL). Recently, surprise has been used as an intrinsic reward that encourages systematic and efficient exploration. We introduce a new definition of surprise and its RL implementation named Variation…

Study on blackjack reinforcement learning performance with varying deck sizes.

Revisits VIC method to correct intrinsic reward bias in stochastic environments.

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that…

New method detects anomalies in systems influenced by their environment.

Bayesian Invariant Prediction models stable features from multi-environment data.

A new RL algorithm tackles PO tasks by modeling the environment and improving the policy.

Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators a…

New method for ancestral inference in branching processes with random environments.

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that…

Jigsaw-VAE tackles feature imbalance in VAE latent variables, improving generalization across environments.

CEA augments reinforcement learning by generating counterfactual experiences.

This paper tackles continuous domain adaptation with a new approach.

Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-st…

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…

In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian modeling framework. We propose to use a neural network for modeling the speech spectro-temporal content. The parameters of this supervised model…

This work uses model uncertainty for efficient exploration in sparse reward environments.

New algorithm improves model generalization in structured biomedical domains.

New method uses unlabeled data to improve model robustness across different environments.

Model-based approaches bear great promise for decision making of agents interacting with the physical world. In the context of spatial environments, different types of problems such as localisation, mapping, navigation or autonomous exploration are typically adressed with specialised methods, often relying on detailed …

LEADS improves model generalization across different environments.

A new neural network model improves reinforcement learning efficiency.

Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is how…

WILD-SCAV benchmarks AI in complex 3D FPS environments.

Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…

Improves RL generalization by minimizing adversarial risk.

Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities. First, we design EscapeRoom environments, where the agent must figure out how to n…

In $\mathcal{X}$-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, su…

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more challenging problems. Most prior work on representation learning has focused on gene…

Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of incomplete and noisy observations. In this paper, we propose d…

Adversarial RL recovers agent rewards from financial market data simulations.

MANGA transfers policies across environments with varying dynamics and noise.

GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.

New algorithm minimizes FE objectives for synthetic AIF agents.

AIF improves physical AI agents' performance in dynamic environments.

New framework for PMD convergence in non-tabular environments.

We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in changing environments. We show how the difficulty posed…

New method learns optimal environment and goal difficulty for reinforcement learning.

GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.

DTS improves robustness of bandit algorithms in nonstationary environments.

Quantum variational circuits improve reinforcement learning efficiency.

Novel framework for data sharing and coordinated exploration in concurrent RL with non-identical environments.

New RL algorithm tackles non-stationary environments with flexible policy updates.

A new variational inference method speeds up AMMI model estimation.

Adaptive linear bandit algorithm with best-of-three-worlds regret bounds.