Search Results for author:
Found 18 papers, 12 papers with code
Verifiably Safe Exploration for End-to-End Reinforcement Learning
We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments.
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e. g., as actions of an agent.
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided.
BISCUIT: Causal Representation Learning from Binary Interactions
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI.
Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions
An important goal common to domain adaptation and causal inference is to make accurate predictions when the distributions for the source (or training) domain(s) and target (or test) domain(s) differ.
Ancestral Causal Inference
Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions.
Graph Switching Dynamical Systems
Dynamical systems with complex behaviours, e. g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes, each with simpler dynamics, and then learning the switching behaviour from one mode to another.
Active Structure Learning of Causal DAGs via Directed Clique Tree
Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG.
Active Structure Learning of Causal DAGs via Directed Clique Trees
Most existing works focus on \textit{worst-case} or \textit{average-case} lower bounds for the number of interventions required to orient a DAG.
Modulated Neural ODEs
Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories.
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities.
Joint Causal Inference from Multiple Contexts
We explain how several well-known causal discovery algorithms can be seen as addressing special cases of the JCI framework, and we also propose novel implementations that extend existing causal discovery methods for purely observational data to the JCI setting.
An Upper Bound for Random Measurement Error in Causal Discovery
Causal discovery algorithms infer causal relations from data based on several assumptions, including notably the absence of measurement error.
Sample Efficient Active Learning of Causal Trees
We consider the problem of experimental design for learning causal graphs that have a tree structure.
Factored Adaptation for Non-Stationary Reinforcement Learning
Dealing with non-stationarity in environments (e. g., in the transition dynamics) and objectives (e. g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL).
A Sparsity Principle for Partially Observable Causal Representation Learning
Causal representation learning aims at identifying high-level causal variables from perceptual data.
Towards the Reusability and Compositionality of Causal Representations
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e. g., images.
