Combining Reinforcement Learning and Tensor Networks, with an Application to Dynamical Large Deviations
This work addresses a domain-specific problem in physics and multi-agent reinforcement learning by providing a novel framework for handling complex optimization tasks, though it is incremental as it combines existing tensor network and reinforcement learning techniques.
The paper tackled the problem of solving dynamical optimization tasks with large, factorizable state and action spaces by integrating tensor networks into reinforcement learning, resulting in the ACTeN method that successfully sampled rare trajectories in stochastic models like the East model and ASEP, which are exponentially hard and challenging for other methods.
We present a framework to integrate tensor network (TN) methods with reinforcement learning (RL) for solving dynamical optimisation tasks. We consider the RL actor-critic method, a model-free approach for solving RL problems, and introduce TNs as the approximators for its policy and value functions. Our "actor-critic with tensor networks" (ACTeN) method is especially well suited to problems with large and factorisable state and action spaces. As an illustration of the applicability of ACTeN we solve the exponentially hard task of sampling rare trajectories in two paradigmatic stochastic models, the East model of glasses and the asymmetric simple exclusion process (ASEP), the latter being particularly challenging to other methods due to the absence of detailed balance. With substantial potential for further integration with the vast array of existing RL methods, the approach introduced here is promising both for applications in physics and to multi-agent RL problems more generally.