Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
This work addresses the problem of generalization in reinforcement learning for agents, offering a novel causal reasoning approach that is incremental in advancing causal RL methods.
The paper tackles the challenge of enabling reinforcement learning agents to generalize to varied goals by integrating causal reasoning, proposing a framework that formulates goal-conditioned RL as variational likelihood maximization with causal graphs as latent variables. It demonstrates effectiveness through nine custom tasks, showing performance improvements against five baselines.
As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and discovering cause-and-effect relations. However, how to discover and represent causalities remains a huge gap that hinders the development of causal RL. In this paper, we augment Goal-Conditioned RL (GCRL) with Causal Graph (CG), a structure built upon the relation between objects and events. We novelly formulate the GCRL problem into variational likelihood maximization with CG as latent variables. To optimize the derived objective, we propose a framework with theoretical performance guarantees that alternates between two steps: using interventional data to estimate the posterior of CG; using CG to learn generalizable models and interpretable policies. Due to the lack of public benchmarks that verify generalization capability under reasoning, we design nine tasks and then empirically show the effectiveness of the proposed method against five baselines on these tasks. Further theoretical analysis shows that our performance improvement is attributed to the virtuous cycle of causal discovery, transition modeling, and policy training, which aligns with the experimental evidence in extensive ablation studies.