Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
ICLR 2025 (poster)
ICLR 2025 (poster)
Abstract
Figure 1: (a). Example of robot manipulation task with three trajectories and three nodes: one target node (movable) and two noisy nodes (one movable, one unmovable). (b). Underlying causal structures of the example.
In Model-Based Reinforcement Learning (MBRL), incorporating causal structures into dynamics models provides agents with a structured understanding of the environments, enabling efficient decision. Empowerment as an intrinsic motivation enhances the ability of agents to actively control their environments by maximizing the mutual information between future states and actions. We posit that empowerment coupled with causal understanding can improve controllability, while enhanced empowerment gain can further facilitate causal reasoning in MBRL. To improve learning efficiency and controllability, we propose a novel framework, Empowerment through Causal Learning (ECL), where an agent with the awareness of causal dynamics models achieves empowerment-driven exploration and optimizes its causal structure for task learning. Specifically, ECL operates by first training a causal dynamics model of the environment based on collected data. We then maximize empowerment under the causal structure for exploration, simultaneously using data gathered through exploration to update causal dynamics model to be more controllable than dense dynamics model without causal structure. In downstream task learning, an intrinsic curiosity reward is included to balance the causality, mitigating overfitting. Importantly, ECL is method-agnostic and is capable of integrating various causal discovery methods. We evaluate ECL combined with 2 causal discovery methods across 6 environments including pixel-based tasks, demonstrating its superior performance compared to other causal MBRL methods, in terms of causal discovery, sample efficiency, and asymptotic performance.
Reach the movable red cube
ECL
CDL
Reach the target red point
ECL
CDL
Tasks learning of ECL
Tasks learning of IFactor