Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

• URL: http://arxiv.org/abs/2305.14133v2
• Date: Thu, 12 Oct 2023 09:18:09 GMT
• Title: Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
• Authors: Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna, Stefano V. Albrecht
• Abstract summary: Reinforcement Learning environments can produce training data with spurious correlations between features. Disentangled representations can improve robustness, but existing disentanglement techniques that minimise mutual information between features require independent features. We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features.
• Score: 13.450394764597663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading correlations in their latent representation, preventing the agent from generalising if the correlation changes within the environment or when deployed in the real world. Disentangled representations can improve robustness, but existing disentanglement techniques that minimise mutual information between features require independent features, thus they cannot disentangle correlated features. We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features by minimising the conditional mutual information between features in the representation. We demonstrate experimentally, using continuous control tasks, that our approach improves generalisation under correlation shifts, as well as improving the training performance of RL algorithms in the presence of correlated features.

Related papers

• Out of spuriousity: Improving robustness to spurious correlations without group annotations [2.592470112714595]
  We propose an approach to extract a subnetwork from a fully trained network that does not rely on spurious correlations. The increase in the worst-group performance of our approach contributes to strengthening the hypothesis that there exists a subnetwork in a fully trained dense network.
  arXiv  Detail & Related papers  (2024-07-20T20:24:14Z)
• Learning Generalizable Agents via Saliency-Guided Features Decorrelation [25.19044461705711]
  We propose Saliency-Guided Features Decorrelation to eliminate correlations between features and decisions. RFF is utilized to estimate the complex non-linear correlations in high-dimensional images, while the saliency map is designed to identify the changed features. Under the guidance of the saliency map, SGFD employs sample reweighting to minimize the estimated correlations related to changed features.
  arXiv  Detail & Related papers  (2023-10-08T09:24:43Z)
• Compressed Regression over Adaptive Networks [58.79251288443156]
  We derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents.
  arXiv  Detail & Related papers  (2023-04-07T13:41:08Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning [2.984934409689467]
  Causal confusion refers to a phenomenon where an agent learns spurious correlations between features which might not hold across the entire state space. We propose ReCCoVER, an algorithm which detects causal confusion in agent's reasoning before deployment.
  arXiv  Detail & Related papers  (2022-03-21T13:17:30Z)
• Disentanglement and Generalization Under Correlation Shifts [22.499106910581958]
  Correlations between factors of variation are prevalent in real-world data. Machine learning algorithms may benefit from exploiting such correlations, as they can increase predictive performance on noisy data. We aim to learn representations which capture different factors of variation in latent subspaces.
  arXiv  Detail & Related papers  (2021-12-29T18:55:17Z)
• Return-Based Contrastive Representation Learning for Reinforcement Learning [126.7440353288838]
  We propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our algorithm outperforms strong baselines on complex tasks in Atari games and DeepMind Control suite.
  arXiv  Detail & Related papers  (2021-02-22T13:04:18Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)
• FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs [53.710405006523274]
  This work focuses on the representation learning question: how can we learn such features? Under the assumption that the underlying (unknown) dynamics correspond to a low rank transition matrix, we show how the representation learning question is related to a particular non-linear matrix decomposition problem. We develop FLAMBE, which engages in exploration and representation learning for provably efficient RL in low rank transition models.
  arXiv  Detail & Related papers  (2020-06-18T19:11:18Z)
• Dynamic Federated Learning [57.14673504239551]
  Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
  arXiv  Detail & Related papers  (2020-02-20T15:00:54Z)

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.