Towards Causal Model-Based Policy Optimization

• URL: http://arxiv.org/abs/2503.09719v1
• Date: Wed, 12 Mar 2025 18:09:02 GMT
• Title: Towards Causal Model-Based Policy Optimization
• Authors: Alberto Caron, Vasilios Mavroudis, Chris Hicks,
• Abstract summary: We introduce Causal Model-Based Policy Optimization (C-MBPO)<n>C-MBPO is a novel framework that integrates causal learning into the Model-Based Reinforcement Learning pipeline.<n>We show that C-MBPO can be shown to be robust to a class of distributional shifts that affect spurious, non-causal relationships in the dynamics.
• Score: 0.24578723416255752
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world decision-making problems are often marked by complex, uncertain dynamics that can shift or break under changing conditions. Traditional Model-Based Reinforcement Learning (MBRL) approaches learn predictive models of environment dynamics from queried trajectories and then use these models to simulate rollouts for policy optimization. However, such methods do not account for the underlying causal mechanisms that govern the environment, and thus inadvertently capture spurious correlations, making them sensitive to distributional shifts and limiting their ability to generalize. The same naturally holds for model-free approaches. In this work, we introduce Causal Model-Based Policy Optimization (C-MBPO), a novel framework that integrates causal learning into the MBRL pipeline to achieve more robust, explainable, and generalizable policy learning algorithms. Our approach centers on first inferring a Causal Markov Decision Process (C-MDP) by learning a local Structural Causal Model (SCM) of both the state and reward transition dynamics from trajectories gathered online. C-MDPs differ from classic MDPs in that we can decompose causal dependencies in the environment dynamics via specifying an associated Causal Bayesian Network. C-MDPs allow for targeted interventions and counterfactual reasoning, enabling the agent to distinguish between mere statistical correlations and causal relationships. The learned SCM is then used to simulate counterfactual on-policy transitions and rewards under hypothetical actions (or ``interventions"), thereby guiding policy optimization more effectively. The resulting policy learned by C-MBPO can be shown to be robust to a class of distributional shifts that affect spurious, non-causal relationships in the dynamics. We demonstrate this through some simple experiments involving near and far OOD dynamics drifts.

Related papers

• Better Decisions through the Right Causal World Model [17.623937562865617]
  Causal Object-centric Model Extraction Tool (COMET) is a novel algorithm designed to learn the exact interpretable causal world models (CWMs) Our results, validated in Atari environments such as Pong and Freeway, demonstrate the accuracy and robustness of COMET.
  arXiv  Detail & Related papers  (2025-04-09T20:29:13Z)
• SAMBO-RL: Shifts-aware Model-based Offline Reinforcement Learning [9.88109749688605]
  Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models.<n>This paper offers a comprehensive analysis that disentangles the problem into two fundamental components: model bias and policy shift.<n>We introduce Shifts-aware Model-based Offline Reinforcement Learning (SAMBO-RL), a practical framework that efficiently trains classifiers to approximate SAR for policy optimization.
  arXiv  Detail & Related papers  (2024-08-23T04:25:09Z)
• Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL [57.202733701029594]
  We propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy. To address these challenges, we propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy. To mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization.
  arXiv  Detail & Related papers  (2024-06-08T10:12:00Z)
• Learning a Diffusion Model Policy from Rewards via Q-Score Matching [93.0191910132874]
  We present a theoretical framework linking the structure of diffusion model policies to a learned Q-function.<n>We propose a new policy update method from this theory, which we denote Q-score matching.
  arXiv  Detail & Related papers  (2023-12-18T23:31:01Z)
• Model-based Causal Bayesian Optimization [74.78486244786083]
  We introduce the first algorithm for Causal Bayesian Optimization with Multiplicative Weights (CBO-MW) We derive regret bounds for CBO-MW that naturally depend on graph-related quantities. Our experiments include a realistic demonstration of how CBO-MW can be used to learn users' demand patterns in a shared mobility system.
  arXiv  Detail & Related papers  (2023-07-31T13:02:36Z)
• Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation [50.93536377097659]
  This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems. The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors.
  arXiv  Detail & Related papers  (2023-04-17T00:10:56Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief [3.0036519884678894]
  Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. In this work, we maintain a belief distribution over dynamics, and evaluate/optimize policy through biased sampling from the belief. We show that the biased sampling naturally induces an updated dynamics belief with policy-dependent reweighting factor, termed Pessimism-Modulated Dynamics Belief.
  arXiv  Detail & Related papers  (2022-10-13T03:14:36Z)
• Causal Dynamics Learning for Task-Independent State Abstraction [61.707048209272884]
  We introduce Causal Dynamics Learning for Task-Independent State Abstraction (CDL) CDL learns a theoretically proved causal dynamics model that removes unnecessary dependencies between state variables and the action. A state abstraction can then be derived from the learned dynamics.
  arXiv  Detail & Related papers  (2022-06-27T17:02:53Z)
• Revisiting Design Choices in Model-Based Offline Reinforcement Learning [39.01805509055988]
  Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies. This paper compares and designs novel protocols to investigate their interaction with other hyper parameters, such as the number of models, or imaginary rollout horizon.
  arXiv  Detail & Related papers  (2021-10-08T13:51:34Z)
• Learning Robust Models Using The Principle of Independent Causal Mechanisms [26.79262903241044]
  We propose a new gradient-based learning framework whose objective function is derived from the ICM principle. We show theoretically and experimentally that neural networks trained in this framework focus on relations remaining invariant across environments.
  arXiv  Detail & Related papers  (2020-10-14T15:38:01Z)
• Invariant Causal Prediction for Block MDPs [106.63346115341862]
  Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. We propose a method of invariant prediction to learn model-irrelevance state abstractions (MISA) that generalize to novel observations in the multi-environment setting.
  arXiv  Detail & Related papers  (2020-03-12T21:03:01Z)

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.