S3: Stable Subgoal Selection by Constraining Uncertainty of Coarse Dynamics in Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution. It has been widely successful in solving long-horizon and complex tasks, where flat-RL algorithms have difficulty in learning. However, while the low-level agent in HRL benefits from dense feedback and abundant trial opportunities, the high-level agent receives sparse, delayed feedback from the environment and its performance depends on the low-level execution capability. In this paper, we study whether subgoal selection by the high-level agent can be performed more strategically, by providing it with dynamics-aware intrinsic motivation. Since motivation based on primitive transition dynamics would require broad coverage of the state-action space, we propose to use coarse dynamics, i.e., environment transitions aggregated over multiple steps at the temporal scale at which the high-level agent operates. This approach stabilizes the high-level policy by learning to minimize the predictive uncertainty associated with the coarse dynamics, and provides a guided structure for navigation. We model the predictive uncertainty by evaluating different dispersion metrics as approximated by a Mixture Density Network (MDN). Empirically, we observe that a dense, dynamics-aware intrinsic reward leads to risk-averse subgoal selection, enabling it to outperform state-of-the-art HRL methods in non-stationary long-horizon environments.

A Unifying Lens on Reward Uncertainty in RLHF

Reinforcement learning from human feedback (RLHF) is bottlenecked by \emph{reward hacking}, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is \emph{pessimism}: penalizing rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a \emph{distributional} reward model $p(r\mid x,y)$. Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward $\tilde r(x,y) = \pmβ\log\mathbb{E}_p[e^{\pm r/β}]$. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.