Fine-grained Causal Dynamics Learning With Quantization For Improving Robustness In Reinforcement Learning

Abstract

Causal dynamics learning has recently emerged as a promising approach to enhancing robustness in reinforcement learning (RL). Typically, the goal is to build a dynamics model that makes predictions based on the causal relationships among the entities. Despite the fact that causal connections often manifest only under certain contexts, existing approaches overlook such fine-grained relationships and lack a detailed understanding of the dynamics. In this work, we propose a novel dynamics model that infers fine-grained causal structures and employs them for prediction, leading to improved robustness in RL. The key idea is to jointly learn the dynamics model with a discrete latent variable that quantizes the state-action space into subgroups. This leads to recognizing meaningful context that displays sparse dependencies, where causal structures are learned for each subgroup throughout the training. Experimental results demonstrate the robustness of our method to unseen states and locally s

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhwang2024fine

Related papers

• Model-invariant State Abstractions For Model-based Reinforcement Learning (2021)0.00
• Extracting Latent State Representations With Linear Dynamics From Rich Observations (2020)0.00
• Dynamic Sparsity: Challenging Common Sparsity Assumptions For Learning World Models In Robotic Reinforcement Learning Benchmarks (2025)0.00
• Quantifying First-order Markov Violations In Noisy Reinforcement Learning: A Causal Discovery Approach (2025)0.00
• Learning Nonlinear Causal Reductions To Explain Reinforcement Learning Policies (2025)0.00
• Learning By Doing: An Online Causal Reinforcement Learning Framework With Causal-aware Policy (2024)1.56
• Iqrl -- Implicitly Quantized Representations For Sample-efficient Reinforcement Learning (2024)0.00
• Towards Causal Model-based Policy Optimization (2025)0.00