Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCausal Reinforcement Learning using Observational and Interventional Data
93
0
0.0
(
0
)
Added by
Maxime Gasse
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct interactions with the environment (interventional data), but has also access to a large collection of offline experiences, obtained by observing another agent interacting with the environment (observational data). A key ingredient, that makes this situation non-trivial, is that we allow the observed agent to interact with the environment based on hidden information, which is not observed by the learning agent. We then ask the following questions: can the online and offline experiences be safely combined for learning a causal model ? And can we expect the offline experiences to improve the agents performances ? To answer these questions, we import ideas from the well-established causal framework of do-calculus, and we express model-based reinforcement learning as a causal inference problem. Then, we propose a general yet simple methodology for leveraging offline data during learning. In a nutshell, the method relies on learning a latent-based causal transition model that explains both the interventional and observational regimes, and then using the recovered latent variable to infer the standard POMDP transition model via deconfounding. We prove our method is correct and efficient in the sense that it attains better generalization guarantees due to the offline data (in the asymptotic case), and we illustrate its effectiveness empirically on synthetic toy problems. Our contribution aims at bridging the gap between the fields of reinforcement learning and causality.
rate research
Read More
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line of work reformulates this problem as a continuous constrained optimization one, which is solved via the augmented Lagrangian method. However, most methods based on this idea do not make use of interventional data, which can significantly alleviate identifiability issues. This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interventional data. We illustrate the flexibility of the continuous-constrained framework by taking advantage of expressive neural architectures such as normalizing flows. We show that our approach compares favorably to the state of the art in a variety of settings, including perfect and imperfect interventions for which the targeted nodes may even be unknown.
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on textit{mini}ImageNet, textit{tiered}ImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.
Convenient access to observational data enables us to learn causal effects without randomized experiments. This research direction draws increasing attention in research areas such as economics, healthcare, and education. For example, we can study how a medicine (the treatment) causally affects the health condition (the outcome) of a patient using existing electronic health records. To validate causal effects learned from observational data, we have to control confounding bias -- the influence of variables which causally influence both the treatment and the outcome. Existing work along this line overwhelmingly relies on the unconfoundedness assumption that there do not exist unobserved confounders. However, this assumption is untestable and can even be untenable. In fact, an important fact ignored by the majority of previous work is that observational data can come with network information that can be utilized to infer hidden confounders. For example, in an observational study of the individual-level treatment effect of a medicine, instead of randomized experiments, the medicine is often assigned to each individual based on a series of factors. Some of the factors (e.g., socioeconomic status) can be challenging to measure and therefore become hidden confounders. Fortunately, the socioeconomic status of an individual can be reflected by whom she is connected in social networks. With this fact in mind, we aim to exploit the network information to recognize patterns of hidden confounders which would further allow us to learn valid individual causal effects from observational data. In this work, we propose a novel causal inference framework, the network deconfounder, which learns representations to unravel patterns of hidden confounders from the network information. Empirically, we perform extensive experiments to validate the effectiveness of the network deconfounder on various datasets.
Machine learning models are often trained on data from one distribution and deployed on others. So it becomes important to design models that are robust to distribution shifts. Most of the existing work focuses on optimizing for either adversarial shifts or interventional shifts. Adversarial methods lack expressivity in representing plausible shifts as they consider shifts to joint distributions in the data. Interventional methods allow more expressivity but provide robustness to unbounded shifts, resulting in overly conservative models. In this work, we combine the complementary strengths of the two approaches and propose a new formulation, RISe, for designing robust models against a set of distribution shifts that are at the intersection of adversarial and interventional shifts. We employ the distributionally robust optimization framework to optimize the resulting objective in both supervised and reinforcement learning settings. Extensive experimentation with synthetic and real world datasets from healthcare demonstrate the efficacy of the proposed approach.
It is a long-standing question to discover causal relations among a set of variables in many empirical sciences. Recently, Reinforcement Learning (RL) has achieved promising results in causal discovery from observational data. However, searching the space of directed graphs and enforcing acyclicity by implicit penalties tend to be inefficient and restrict the existing RL-based method to small scale problems. In this work, we propose a novel RL-based approach for causal discovery, by incorporating RL into the ordering-based paradigm. Specifically, we formulate the ordering search problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for~each ordering. A generated ordering would then be processed using variable selection to obtain the final causal graph. We analyze the consistency and computational complexity of the proposed method, and empirically show that a pretrained model can be exploited to accelerate training. Experimental results on both synthetic and real data sets shows that the proposed method achieves a much improved performance over existing RL-based method.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
