cs.LGMay 29, 2026

Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments

Authors: Nishant Kumar, Enrique Areyan Viqueira, Amy Greenwald

Abstract

Bidding in repeated auctions is a central challenge for reinforcement learning (RL), combining continuous control with the strategic complexities of digital advertising. While policy gradient and value-based methods seem well-suited for these settings, they often struggle with the discontinuous, "cliff-like" nature of auction reward landscapes. In a first-price auction, for example, a bidder receives zero reward until they cross a specific threshold, after which the reward decreases as the bid increases. This creates a landscape of flat, zero-reward regions separated by sharp boundaries. We identify a fundamental failure mode in this setting termed "zero collapse." We show that stochastic exploration and gradient-based updates can cause policies to overshoot optimal high-reward regions and enter flat, zero-reward regimes. Once there, the lack of an informative gradient signal makes recovery extremely sample-inefficient, effectively trapping the agent. We find that actor-critic methods are particularly susceptible, as biased value estimates can accelerate this movement toward unstable regions. Our contributions include: (1) a mechanistic explanation of how discontinuous rewards lead to vanishing signals and zero collapse; (2) an analysis of the interaction between policy stochasticity and step size; and (3) an empirical demonstration of this phenomenon across REINFORCE and actor-critic variants. We propose practical mitigation strategies involving initialization and architectural choices to improve stability. Finally, we introduce a formal RL framework for auction environments highlighting their unique structural properties.

Explore similar work

CardsList
Jun 19, 2026cs.LG

Discretizing Reward Models

Despite their widespread use, the role of reward models in shaping reinforcement learning is poorly understood. Reward models offer a tempting promise: they automatically estimate response quality in the absence of verifiers or human judges. Unlike "verifiable rewards" which typically produce binary scores, reward models typically produce continuous scores, allowing them to be sensitive to fine-grained differences in responses. However, we show this apparent strength is a serious weakness: many popular reward models are oversensitive, assigning different scores to equally good responses. Theoretically, we show that seemingly perfect reward models can be highly oversensitive; empirically, this oversensitivity can lead to bad policies. In place of existing notions of "reward model accuracy," we propose evaluating reward models using distinct measures of "discriminative ability" and "specificity" (the complement of oversensitivity). As a solution, we describe a training-free algorithm that uses Monte Carlo dropout on any neural reward model to produce discrete reward clusters. Theoretically, we prove there exist discretizations that reduce oversensitivity at minimal expense of discriminative ability; empirically we show, in both controlled and natural RL settings, that discretizing rewards leads to less reward hacking and better policies than training on the original rewards.
Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika +4
Monte CarloOverconfidenceResponses
AskPDF
May 29, 2026cs.LG

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with ReMax, an objective that evaluates a policy by the expected maximum return over MM samples, where MM is a positive integer, while accounting for return uncertainty. Optimizing this objective induces stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a new policy-gradient formulation for ReMax and introduce ReMax PPO (RePPO), a PPO variant that optimizes ReMax while generalizing the discrete retry count MM to a continuous parameter m>0m > 0, enabling fine-grained control of exploration. Empirically, RePPO promotes exploration, without any explicit exploration bonuses, on the MinAtar and Craftax benchmarks.
Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada +4
Stochastic ExplorationRetryingCuriosity-Driven ExplorationEmergence
AskPDF
May 4, 2026cs.AI

ANO: A Principled Approach to Robust Policy Optimization

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the optimization to unbounded updates, causing severe instability and policy collapse during extreme outlier encounters. To resolve this dilemma, we introduce a principled design space for policy optimization, demonstrating that a robust estimator must inherently suppress outliers while maintaining a smooth restoration force. Guided by these geometric principles, we derive Anchored Neighborhood Optimization (ANO), a novel method that seamlessly replaces hard clipping with a redescending gradient mechanism. Extensive evaluations demonstrate ANO's empirical superiority across diverse domains. In continuous (MuJoCo) and discrete (Atari) control, ANO establishes a robust state-of-the-art, uniquely preventing policy collapse even under highly aggressive learning rates (1×10−31 \times 10^{-3}). Furthermore, in LLM alignment (RLHF), ANO explicitly eliminates the catastrophic KL divergence explosion inherent to unconstrained methods, dominating PPO, SPO, and GRPO in head-to-head win rates.
Yiheng Zhang, Yiming Wang, Kaiyan Zhao +3
Proximal Policy OptimizationPolicy OptimizationCollapseOutliersPrinciples
AskPDF