Maximum Entropy Exploration Without the Rollouts

• URL: http://arxiv.org/abs/2603.12325v1
• Date: Thu, 12 Mar 2026 18:00:03 GMT
• Title: Maximum Entropy Exploration Without the Rollouts
• Abstract summary: principled iteration of the exploration problem is to find policies that maximize the entropy of their induced steady-state visitation distribution.<n>In this work, we consider an intrinsic average-reward in which the reward is derived from the visitation distribution itself, so that the optimal policy maximizes steady-state entropy.<n>This insight leads to a novel algorithm for solving the maximum entropy exploration problem, EVE, which avoids explicit rollouts and distribution estimation.
• Score: 5.008597638379228
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when an external reward function is unavailable. A principled formulation of the exploration problem is to find policies that maximize the entropy of their induced steady-state visitation distribution, thereby encouraging uniform long-run coverage of the state space. Many existing exploration approaches require estimating state visitation frequencies through repeated on-policy rollouts, which can be computationally expensive. In this work, we instead consider an intrinsic average-reward formulation in which the reward is derived from the visitation distribution itself, so that the optimal policy maximizes steady-state entropy. An entropy-regularized version of this objective admits a spectral characterization: the relevant stationary distributions can be computed from the dominant eigenvectors of a problem-dependent transition matrix. This insight leads to a novel algorithm for solving the maximum entropy exploration problem, EVE (EigenVector-based Exploration), which avoids explicit rollouts and distribution estimation, instead computing the solution through iterative updates, similar to a value-based approach. To address the original unregularized objective, we employ a posterior-policy iteration (PPI) approach, which monotonically improves the entropy and converges in value. We prove convergence of EVE under standard assumptions and demonstrate empirically that it efficiently produces policies with high steady-state entropy, achieving competitive exploration performance relative to rollout-based baselines in deterministic grid-world environments.

Related papers

• Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control [77.8471519867791]
  Empirically, we show that entropy polarity reliably predicts entropy changes.<n>We propose Polarity-Aware Policy Optimization (PAPO), which preserves both polarity branches and implements entropy control through advantage reweighting.
  arXiv  Detail & Related papers  (2026-05-12T08:47:05Z)
• Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation [33.15281300187744]
  Reinforcement learning with rewards has advanced the reasoning capabilities of large language models.<n>It faces a limitation termed textitrestricted exploration, where the policy rapidly converges to a narrow set of solutions.<n>We propose textbfAsymGRPO, an exploratory framework that explicitly decouples the modulation of positive and negative rollouts.
  arXiv  Detail & Related papers  (2026-04-06T17:42:38Z)
• SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation [54.537828696303286]
  In unsupervised-training for reinforcement learning, the agent aims to learn a prior policy for downstream tasks without relying on task-specific reward functions.<n>We focus on state entropy (SEM), where the goal is to learn a policy that maximizes the entropy of the state stationary distribution.<n>We introduce SEMDICE, a principled off-policy algorithm that computes an SEM policy from an arbitrary off-policy dataset.
  arXiv  Detail & Related papers  (2025-12-10T19:50:21Z)
• Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning [55.59724323303857]
  We propose a framework that balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.<n>Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability.
  arXiv  Detail & Related papers  (2025-10-13T03:10:26Z)
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models [99.98293908799731]
  This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy.<n>In practice, we establish a transformation equation R=-a*eH+b between entropy H and downstream performance R.<n>We propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively.
  arXiv  Detail & Related papers  (2025-05-28T17:38:45Z)
• Entropy annealing for policy mirror descent in continuous time and space [2.8255028200738455]
  We study the impact of entropy regularization on the convergence of policy methods for exit time control problems.<n>This paper explains how entropy regularization improves policy optimization, even with the true gradient.
  arXiv  Detail & Related papers  (2024-05-30T17:02:18Z)
• Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning [9.779769486156631]
  Herein agent interacts with the environment by generating noisy controls distributed according to the optimal relaxed policy. This exploration-exploitation trade-off is determined by the strength of entropy regularisation. We prove that the regret, for both learning algorithms, is of the order $mathcalO(sqrtN) $ (up to a logarithmic factor) over $N$ episodes, matching the best known result from the literature.
  arXiv  Detail & Related papers  (2022-08-08T23:36:40Z)
• k-Means Maximum Entropy Exploration [55.81894038654918]
  Exploration in continuous spaces with sparse rewards is an open problem in reinforcement learning. We introduce an artificial curiosity algorithm based on lower bounding an approximation to the entropy of the state visitation distribution. We show that our approach is both computationally efficient and competitive on benchmarks for exploration in high-dimensional, continuous spaces.
  arXiv  Detail & Related papers  (2022-05-31T09:05:58Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.