ATLAS separates invariant and transferable latent factors across diverse environments.
problem Transfer learning and robust prediction in heterogeneous environments.
method ATLAS leverages invariance principle to disentangle latent factors and uses auxiliary labels for robust prediction.
result Near-oracle performance and robust transferable prediction in new environments.
Bayesian model for multi-environment prediction with latent variable changes.
problem Prediction in environments with changing latent variable distributions.
method Bayesian model with empirical Bayes prior and amortized variational algorithm.
result Method outperforms previous approaches in new environments.
New method recovers causal DAGs from general environments without strict assumptions.
problem Recovering causal DAGs from real-world data with varying distributions.
method Formalizes desiderata for causal representation learning in general environments, leveraging sufficient change conditions up to third-order derivatives.
result Fully recovers latent DAG and identifies latent variables up to minor indeterminacies under nonparametric mixing.
Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…
Jigsaw-VAE tackles feature imbalance in VAE latent variables, improving generalization across environments.
problem Feature imbalance in VAE latent variables leads to poor generalization and biased sample generation.
method Proposes a regularization scheme to balance features in VAE latent variables and introduces a metric to measure balance.
result The regularization scheme substantially addresses feature imbalance, leading to improved generalization and diverse sample generation.
New approach predicts under latent shifts using high-dimensional images.
problem Prediction under latent subgroup shifts with high-dimensional observations.
method Recognition-parametrised model (RPM) for identifying causal latent structure.
result Successfully adapts predictions for high-dimensional image data.
OBSER framework infers sub-environments from objects, outperforming scene-based methods.
problem Zero-shot recognition of environments from object distributions.
method Bayesian framework using metric and self-supervised learning models to estimate object distributions in latent space.
result OBSER framework reliably performs inference in open-world and photorealistic environments, outperforming scene-based methods.
Tree-based regularization improves latent variable inference from related datasets.
problem Inferring latent variables from multiple related datasets in causal systems.
method Tree-Based Regularization (TBR) for sparse changes across environments.
result TBR identifies true latent variables up to simple transformations under sparse changes.
Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment …
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…
Paper establishes identifiability and achievability for causal representation learning.
problem Identifying and recovering latent causal models and variables from observational and interventional data.
method Establishes identifiability and achievability using uncoupled interventions and a recovery algorithm.
result Guaranteed perfect recovery of latent causal model and variables under uncoupled interventions.
Study identifies latent variables and causal relationships from multiple environments.
problem Identify latent variables and causal relationships from multiple environments.
method Proposes algorithm LiNGCReL for identifying causal graph up to surrounded-node ambiguity.
result Identifies latent variables up to surrounded-node ambiguity (SNA) in linear causal models.
A method for self-supervised representation learning in partially observable environments.
problem Sparse rewards and stochasticity in partially observable environments.
method World model in latent space for estimating missing information.
result Significant improvement in exploration compared to prior work.
In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure th…
We solve continuous-time latent SDE identifiability using diffusion shifts.
problem Identifiability of latent SDEs in continuous-time time series.
method Environment-induced shifts in diffusion covariance for additive-noise latent SDEs.
result Two diagonal diffusion regimes with distinct variance ratios identify latent coordinates up to permutation and scaling.
Algorithm improves imitation learning from visual data in partially observable environments.
problem Imitation learning from visual observations with missing expert actions and partial observability.
method Theoretical analysis and Latent Adversarial Imitation from Observations algorithm combining adversarial and latent representations.
result Latent Adversarial Imitation from Observations achieves state-of-the-art performance in high-dimensional robotic tasks.
Sequence models quantify uncertainty over latent concepts.
problem Quantifying uncertainty in latent environments.
method Exchangeable sequence models, equivalent to empirical Bayes and posterior inference.
result Sequence prediction loss controls uncertainty quantification.
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
Proposes method to learn state abstractions that generalize across environments.
problem Learning abstractions that generalize in block MDPs.
method Invariant causal prediction to learn model-irrelevant state abstractions (MISA).
result Proves high probability of outputting a state abstraction corresponding to causal feature set for return.
Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
We identify which latent factors change between environments in linear causal models.
problem Identify latent factors that change between environments in linear causal models with fewer than d interventions. method Propose a method to identify shifted nodes in a smaller number of environments with coarser interventions.
result It is possible to identify the set of shifted nodes under mild assumptions.
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized latent space model that is trained via the minimization of two tractable losses: pr…
Model-based reinforcement learning methods typically learn models for high-dimensional state spaces by aiming to reconstruct and predict the original observations. However, drawing inspiration from model-free reinforcement learning, we propose learning a latent dynamics model directly from rewards. In this work, we int…
Decentralized learning for matching markets with time-varying preferences.
problem Matching between competing agents and supply arms with time-varying preferences.
method Linear contextual bandit framework, learning algorithms to identify latent environment and stable matchings.
result Achieve instance-dependent logarithmic regret, applicable for large markets.
We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obst…
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training…
The paper shows how to learn causal representations with few environments and finite samples.
problem Learning causal representations from limited data and environments.
method Explicit, finite-sample guarantees with a logarithmic number of interventions.
result Consistent recovery of latent causal graph, mixing matrix, and unknown intervention targets.
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.
problem Exploration in visually complex environments.
method Optimizes a single prediction loss in latent space to learn world representation, dynamics, and exploration policy.
result Achieves superhuman performance on Atari games with simpler design.
UWM-JEPA predicts future scenarios in belief space, improving accuracy in partially observed environments.
problem Predicting future scenarios in partially observed environments with uncertainty.
method Introduces UWM-JEPA, a JEPA world model with a density-matrix latent and learned unitary predictor.
result UWM-JEPA achieves 0.77 accuracy on a hidden-velocity indicator task, outperforming LSTM-JEPA.
Identifies latent actions and dynamics from offline data with diverse demonstrators.
problem Recovering latent actions and environment dynamics from action-free trajectories.
method Assumes distinct policies for each demonstrator, identifies latent transitions and policies via matrix factorization.
result Identifies latent transitions and demonstrator policies up to permutation.
Develops RL algorithm for lifelong non-stationary environments.
problem Challenges of reinforcement learning in environments with persistent change.
method Formalizes lifelong non-stationarity, uses latent variable models, and leverages online learning and probabilistic inference.
result Substantial improvement in performance over non-reasoning approaches in lifelong non-stationary environments.
New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.
problem Challenges in planning for stochastic and partially-observable environments.
method Uses discrete autoencoders and a stochastic variant of Monte Carlo tree search.
result Significantly outperforms MuZero on stochastic chess and scales to DeepMind Lab.
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over few episodes during adaptation phase to maximize the return in the test phase. In…
Agent decides when to measure latent states in RL to improve efficiency.
problem Costly state measurement in RL negatively affects future outcomes.
method Introduces AOMDP with measurement action, uses online RL and sequential Monte Carlo.
result Reduced uncertainty improves sample efficiency and policy value.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential d…
LC-SAC tackles non-stationary dynamics in reinforcement learning.
problem Degradation of deep RL methods in non-stationary environments.
method LC-SAC uses latent context encoders and contrastive loss for dynamic information capture.
result LC-SAC outperforms SAC on environments with drastic dynamics changes.
This research tackles intervention-centric causal reasoning in learning agents by using meta-learning.
problem Learning agents lack the concept of interventions, making causal learning challenging.
method A meta-reinforcement learning algorithm is used to learn causal relationships from observational data.
result The approach enables agents to learn and manipulate the environment effectively.
A framework for learning disentangled representations of symmetric environments.
problem Discovering and modelling the underlying structure of environments.
method Group representation theory for disentangled representations of dynamical environments.
result Our method enables accurate long-horizon predictions and correlates with disentanglement quality.
Algorithm finds latent structure in value functions for improved reinforcement learning.
problem Finding latent structure in value functions for efficient reinforcement learning.
method Proposes a practical algorithm using two posterior distributions over state abstractions and abstract-state values.
result Substantial performance gains in multi-task settings where tasks share a common, low-dimensional representation.
MIRO learns robust latent spaces by maximizing mutual information with future information.
problem Robust perception in complex, unstructured environments with low sample complexity.
method MIRO maximizes mutual information in a latent space for model-based reinforcement learning.
result MIRO outperforms reconstruction objectives in cluttered scenes.
This paper presents a new method for medical diagnosis of neurodegenerative diseases, such as Parkinson's, by extracting and using latent information from trained Deep convolutional, or convolutional-recurrent Neural Networks (DNNs). In particular, our approach adopts a combination of transfer learning, k-means cluster…
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.
New method learns near-optimal policies with polynomial samples in A and H.
problem Episodic latent MABs with partial observations are challenging.
method Experiment design and method-of-moments approach.
result Polynomial samples in A and H for near-optimal policy learning.
This paper tackles CRL for multi-node interventions, achieving identifiability guarantees.
problem CRL under unknown multi-node interventions, focusing on single-node assumptions.
method Establishes identifiability results for general latent causal models under stochastic interventions.
result Identifiability up to ancestors using soft interventions, perfect identifiability using hard interventions.
Curiosity-driven exploration using Bayesian surprise in latent space.
problem Enhance exploration capabilities in reinforcement learning.
method Apply Bayesian surprise in a latent space to favor exploration.
result Our method is computationally cheap and performs well on various tasks.
Paper uses deep learning to make predictions transparently.
problem Lack of transparency in DNN predictions.
method Extracts latent variables from trained DNNs for unified analysis.
result Improved prediction accuracy and transparency.
Knowledge of the channel state information (CSI) at the transmitter side is one of the primary sources of information that can be used for the efficient allocation of wireless resources. Obtaining downlink (DL) CSI in Frequency Division Duplexing (FDD) systems from uplink (UL) CSI is not as straightforward as in TDD sy…
Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL). But most of the algorithms focus on learning a single best policy to perform a given set of tasks. I…