cs.LGJan 30, 2026

Constrained Bilevel Reinforcement Learning via Approximate Lower-Level Responses

Authors: Naman Saxena, Vaneet Aggarwal

Organizations: Purdue University, West Lafayette, US

Abstract

We study constrained bilevel reinforcement learning in which the lower-level problem is a constrained Markov decision process with a generally parameterized policy. The lower-level solution map can be set-valued and need not be Lipschitz continuous in the upper-level variable, so standard hypergradient analyses do not apply. We therefore define the upper-level objective as the expected upper-level loss of the policy returned by a fixed stochastic lower-level algorithm, which we call the approximate response. This objective is well defined without uniqueness of the lower-level solution. To compute its gradient, we randomize the reward and constraint values used during lower-level training without changing their means, so that the upper-level variable affects training only through known probabilities. This yields an unbiased estimator of the upper-level objective's gradient that does not differentiate through the lower-level updates. We establish lower-level reward and feasibility guarantees, upper-level stationarity, and a total sample complexity of O~(δℓ−6εo−2)\widetilde{\mathcal{O}}(δ_\ell^{-6}ε_o^{-2}) over both levels, where δℓδ_\ell is the lower-level accuracy and εoε_o is the upper-level stationarity error. Setting δℓ=εo=εδ_\ell=ε_o=ε gives O~(ε−8)\widetilde{\mathcal{O}}(ε^{-8}).

Figures & tables

Explore similar work

Nov 1, 2026

Improved Sample Complexity Analysis For First Order Bilevel Reinforcement Learning

Bilevel reinforcement learning optimizes an upper-level objective through the policy response to a lower-level reinforcement learning problem. Such problems arise when learning a reward model while adapting a policy to that reward. However, a gap remains between sample-complexity guarantees and practical actor--critic training. Tabular analyses restrict applicability to finite spaces, while continuous-state analyses often impose a uniform Polyak--Łojasiewicz (PL) condition. We show that this condition need not hold even for smooth positive policies with exactly representable values. We develop a single-loop, fully first-order method for continuous states and finite actions with specified multilayer neural actors and a persistently trained nonlinear critic built from fixed features. Under explicit initialization, regularity, feature-excitation, and value-realizability conditions, fixed reference-KL regularization yields local curvature, and we prove containment of the coupled iterates. Shared trajectories control sampling noise, while paired critic analysis controls normalized critic-error differences as the response perturbation shrinks. A joint descent and tracking argument establishes an improved O~(ε−2)\widetilde{\mathcal O}(\varepsilon^{-2}) sample complexity for O(ε)O(\varepsilon) expected squared gradient norm of the upper objective induced by the selected regularized policy response, including critic training.
Jul 30, 2026

Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity

Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hierarchical task decomposition, and reinforcement learning from human feedback (RL-HF). Most of the bilevel RL algorithms are either not scalable because of using hypergradient with Hessian, or they suffer from high sample complexity because of using penalty-based approximation methods. In this work, we propose a hypergradient-based bilevel RL algorithm using the optimality of the Boltzmann policy for the entropy regularized discounted RL objective function. Our proposed algorithm is Hessian-free and obtains an iteration complexity of O(ε−1)O(ε^{-1}) and state-of-the-art sample complexity of O~(ε−2)\tilde{O}(ε^{-2}) under mild regularity conditions. Further, in our convergence analysis, we are able to remove the assumption of the Polyak-Lojasiewicz (PL) condition on the outer-level objective function present in the prior state-of-the-art sample complexity work.
Nov 9, 2026

Reward-Estimated Hypergradient for Bilevel Reinforcement Learning with Black-Box Follower

Hypergradient (HG) methods for bilevel reinforcement learning (RL) typically assume a white-box follower whose reward is known. In practice, however, the leader rarely knows the follower's reward function and can only observe its trajectories. We address this black-box setting and propose Reward-Estimated Hypergradients (RE-HG), which recovers the follower's reward from these trajectories via inverse RL (IRL). Yet IRL identifies the reward only up to potential-based shaping, a transformation that leaves the follower's behavior unchanged but biases the HG. We prove that, for linear rewards, this bias cancels when IRL estimates are aggregated across sufficiently diverse dynamics, which the leader's own updates naturally supply. To handle finite samples, RE-HG truncates small eigenvalues of the aggregated feature covariance, restoring the identifiable subspace and stabilizing the estimation. Experiments show that RE-HG estimates gradients aligned with a white-box Oracle and achieves comparable performance; empirically, the truncation also suppresses HG explosions, letting RE-HG avoid local optima that trap the Oracle in sharp reward landscapes.