Causal Action Influence Aware Counterfactual Data Augmentation
- URL: http://arxiv.org/abs/2405.18917v1
- Date: Wed, 29 May 2024 09:19:50 GMT
- Title: Causal Action Influence Aware Counterfactual Data Augmentation
- Authors: Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica, Georg Martius,
- Abstract summary: We propose CAIAC, a data augmentation method that can create synthetic transitions from a fixed dataset without having access to online environment interactions.
By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping $itaction$-unaffected parts of the state-space.
This leads to a substantial increase in robustness of offline learning algorithms against distributional shift.
- Score: 23.949113120847507
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online environment interactions. By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping $\it{action}$-unaffected parts of the state-space between independent trajectories in the dataset. We empirically show that this leads to a substantial increase in robustness of offline learning algorithms against distributional shift.
Related papers
- Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [94.2860766709971]
We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a wireless network with statistically-identical agents.
Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies.
arXiv Detail & Related papers (2024-04-04T06:24:11Z) - Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data [17.991833729722288]
We propose a novel policy learning algorithm, PESsimistic CAusal Learning (PESCAL)
Our key observation is that, by incorporating auxiliary variables that mediate the effect of actions on system dynamics, it is sufficient to learn a lower bound of the mediator distribution function, instead of the Q-function.
We provide theoretical guarantees for the algorithms we propose, and demonstrate their efficacy through simulations, as well as real-world experiments utilizing offline datasets from a leading ride-hailing platform.
arXiv Detail & Related papers (2024-03-18T14:51:19Z) - What Can We Learn from Unlearnable Datasets? [107.12337511216228]
Unlearnable datasets have the potential to protect data privacy by preventing deep neural networks from generalizing.
It is widely believed that neural networks trained on unlearnable datasets only learn shortcuts, simpler rules that are not useful for generalization.
In contrast, we find that networks actually can learn useful features that can be reweighed for high test performance, suggesting that image protection is not assured.
arXiv Detail & Related papers (2023-05-30T17:41:35Z) - Causal Decision Transformer for Recommender Systems via Offline
Reinforcement Learning [23.638418776700522]
We propose a new model named the causal decision transformer for recommender systems (CDT4Rec)
CDT4Rec is an offline reinforcement learning system that can learn from a dataset rather than from online interaction.
To demonstrate the feasibility and superiority of our model, we have conducted experiments on six real-world offline datasets and one online simulator.
arXiv Detail & Related papers (2023-04-17T00:05:52Z) - Personalized Decentralized Multi-Task Learning Over Dynamic
Communication Graphs [59.96266198512243]
We propose a decentralized and federated learning algorithm for tasks that are positively and negatively correlated.
Our algorithm uses gradients to calculate the correlations among tasks automatically, and dynamically adjusts the communication graph to connect mutually beneficial tasks and isolate those that may negatively impact each other.
We conduct experiments on a synthetic Gaussian dataset and a large-scale celebrity attributes (CelebA) dataset.
arXiv Detail & Related papers (2022-12-21T18:58:24Z) - Mechanisms that Incentivize Data Sharing in Federated Learning [90.74337749137432]
We show how a naive scheme leads to catastrophic levels of free-riding where the benefits of data sharing are completely eroded.
We then introduce accuracy shaping based mechanisms to maximize the amount of data generated by each agent.
arXiv Detail & Related papers (2022-07-10T22:36:52Z) - Causal Reinforcement Learning using Observational and Interventional
Data [14.856472820492364]
Learning efficiently a causal model of the environment is a key challenge of model RL agents operating in POMDPs.
We consider a scenario where the learning agent has the ability to collect online experiences through direct interactions with the environment.
We then ask the following questions: can the online and offline experiences be safely combined for learning a causal model.
arXiv Detail & Related papers (2021-06-28T06:58:20Z) - DEALIO: Data-Efficient Adversarial Learning for Imitation from
Observation [57.358212277226315]
In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator.
Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms.
This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk.
We propose a more data-efficient IfO algorithm
arXiv Detail & Related papers (2021-03-31T23:46:32Z) - Offline Learning for Planning: A Summary [0.0]
Training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment.
Data sets containing recorded experiences of intelligent agents performing various tasks are accessible on the internet.
In this paper we adumbrate the ideas motivating the development of the state-of-the-art offline learning baselines.
arXiv Detail & Related papers (2020-10-05T11:41:11Z) - Provably Efficient Causal Reinforcement Learning with Confounded
Observational Data [135.64775986546505]
We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting.
We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
arXiv Detail & Related papers (2020-06-22T14:49:33Z) - Causal Discovery from Incomplete Data: A Deep Learning Approach [21.289342482087267]
Imputated Causal Learning is proposed to perform iterative missing data imputation and causal structure discovery.
We show that ICL can outperform state-of-the-art methods under different missing data mechanisms.
arXiv Detail & Related papers (2020-01-15T14:28:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.