Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

• URL: http://arxiv.org/abs/2606.03962v1
• Date: Tue, 02 Jun 2026 17:50:14 GMT
• Title: Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
• Abstract summary: We argue that diversity is more naturally understood as the rational response to uncertainty in the reward.<n>We propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions.
• Score: 31.44259732617169
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require fragile trade-offs that sacrifice performance for stochasticity or rely on heuristic metrics that can misalign policy rankings. We argue that diversity is more naturally understood as the rational response to uncertainty in the reward. When the reward function is not perfectly known--as is the case with ambiguous preferences or imperfect reward models--committing to a single action can be sub-optimal. Building on this, we propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions, and applying a non-linear objective over sets of actions. The result is a framework in which calibrated behavioural diversity emerges naturally, remains controllable through the reward function distribution, and is obtained without sacrificing expected reward. Focusing on the contextual bandit setting, we derive a principled gradient estimator for this objective and prove that our formulation naturally generalizes both vanilla policy gradient and more recently developed action-set approaches. Our empirical results demonstrate that this framework offers a robust and theoretically grounded alternative for complex RL tasks where the traditional formulation of the problem fails to induce the desired breadth of agent behaviour.

Related papers

• Inference-Time Policy Alignment for Fair Reinforcement Learning [1.9342617041096457]
  Policy of deep reinforcement learning agents is often rigid and costly to adapt to new performance criteria.<n>We propose a multiplicative policy shaping framework that adjusts action probabilities using action-dependent welfare scores.<n>Our framework is general and compatible with any deep RL agent.
  arXiv  Detail & Related papers  (2026-07-31T18:00:50Z)
• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning [58.088509347353465]
  Reinforcement learning (RL) fine-tuning is widely used in language model training.<n>We propose a game-theoretic framework that gives this trade-off an explicit statistical interpretation.
  arXiv  Detail & Related papers  (2026-07-29T00:19:09Z)
• Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization [52.74762030521324]
  We propose a novel algorithm to learn reward functions from observed actions.<n>We provide strong theoretical guarantees for the reliability and sample efficiency of our algorithm.
  arXiv  Detail & Related papers  (2026-01-19T04:12:51Z)
• GARDO: Reinforcing Diffusion Models without Reward Hacking [54.841464430913476]
  Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment.<n>The mismatch often leads to reward hacking, where proxy scores increase while real image quality deteriorates and generation diversity collapses.<n>We propose Gated and Adaptive Regularization with Diversity-aware Optimization (GARDO) to address the competing demands of sample efficiency, effective exploration, and mitigation of reward hacking.
  arXiv  Detail & Related papers  (2025-12-30T10:55:45Z)
• Statistical analysis of Inverse Entropy-regularized Reinforcement Learning [15.054399128586232]
  Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs.<n>Many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed.<n>We develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning.
  arXiv  Detail & Related papers  (2025-12-07T18:26:19Z)
• Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids [37.79354987519793]
  We study the problem of generalizing an expert agent's behavior, provided through demonstrations, to new environments and/or additional constraints.<n>We propose a novel, principled criterion that selects the "average" policy among those induced by the rewards in a certain bounded subset of the feasible set.
  arXiv  Detail & Related papers  (2025-09-15T14:53:54Z)
• Recursive Reward Aggregation [60.51668865089082]
  We propose an alternative approach for flexible behavior alignment that eliminates the need to modify the reward function.<n>By introducing an algebraic perspective on Markov decision processes (MDPs), we show that the Bellman equations naturally emerge from the generation and aggregation of rewards.<n>Our approach applies to both deterministic and deterministic settings and seamlessly integrates with value-based and actor-critic algorithms.
  arXiv  Detail & Related papers  (2025-07-11T12:37:20Z)
• Probabilistic Uncertain Reward Model [27.40414952747553]
  This paper proposes the Probabilistic Uncertain Reward Model (PURM) to learn the reward distributions that emerged from the preference data.<n>We show that PURM outperforms existing methods with more accurate reward and sound uncertainty estimations.
  arXiv  Detail & Related papers  (2025-03-28T14:39:52Z)
• Likelihood Reward Redistribution [0.0]
  We propose a emphLikelihood Reward Redistribution (LRR) framework for reward redistribution.<n>When integrated with an off-policy algorithm such as Soft Actor-Critic, LRR yields dense and informative reward signals.
  arXiv  Detail & Related papers  (2025-03-20T20:50:49Z)
• Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning [0.5524804393257919]
  We show how a simple linear shift of the potential function can be used to improve the effectiveness of reward shaping.<n>We show the theoretical limitations of continuous potential functions for correctly assigning positive and negative reward shaping values.
  arXiv  Detail & Related papers  (2025-02-03T12:32:50Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
  We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk. Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
  arXiv  Detail & Related papers  (2021-06-11T16:49:15Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)

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.