Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2509.24047v1
• Date: Sun, 28 Sep 2025 19:44:59 GMT
• Title: Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
• Authors: Runyu Zhang, Na Li, Asuman Ozdaglar, Jeff Shamma, Gioele Zardini,
• Abstract summary: We propose a principled framework that interprets risk-seeking objectives as optimism.<n>We derive a policy-gradient theorem for optimistic value functions, including explicit formulas for the entropic risk/KL-penalty setting.<n>Our framework thus unifies risk-sensitive learning and optimism, offering a theoretically grounded and practically effective approach to cooperation in MARL.
• Score: 3.2693858240177565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Risk sensitivity has become a central theme in reinforcement learning (RL), where convex risk measures and robust formulations provide principled ways to model preferences beyond expected return. Recent extensions to multi-agent RL (MARL) have largely emphasized the risk-averse setting, prioritizing robustness to uncertainty. In cooperative MARL, however, such conservatism often leads to suboptimal equilibria, and a parallel line of work has shown that optimism can promote cooperation. Existing optimistic methods, though effective in practice, are typically heuristic and lack theoretical grounding. Building on the dual representation for convex risk measures, we propose a principled framework that interprets risk-seeking objectives as optimism. We introduce optimistic value functions, which formalize optimism as divergence-penalized risk-seeking evaluations. Building on this foundation, we derive a policy-gradient theorem for optimistic value functions, including explicit formulas for the entropic risk/KL-penalty setting, and develop decentralized optimistic actor-critic algorithms that implement these updates. Empirical results on cooperative benchmarks demonstrate that risk-seeking optimism consistently improves coordination over both risk-neutral baselines and heuristic optimistic methods. Our framework thus unifies risk-sensitive learning and optimism, offering a theoretically grounded and practically effective approach to cooperation in MARL.

Related papers

• Robust Bayesian Dynamic Programming for On-policy Risk-sensitive Reinforcement Learning [4.71677151409532]
  We propose a novel framework for risk-sensitive reinforcement learning that incorporates robustness against transition uncertainty.<n>Our framework unifies and generalizes most existing RL frameworks by permitting general coherent risk measures for both inner and outer risk measures.
  arXiv  Detail & Related papers  (2025-12-31T03:13:22Z)
• RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training [13.309653291779233]
  Reinforcement learning with verifiable reward has emerged as a central paradigm for post-training large language models (LLMs)<n>We argue that these issues stem from overemphasizing high-probability output sequences while neglecting rare but informative reasoning paths.<n>We propose Risk-based Policy Optimization (RiskPO), which substitutes classical mean-based objectives with principled risk measures.
  arXiv  Detail & Related papers  (2025-10-01T13:53:09Z)
• Risk-Averse Best Arm Set Identification with Fixed Budget and Fixed Confidence [0.562479170374811]
  We introduce a novel problem setting in bandit optimization that addresses maximizing expected reward and minimizing associated uncertainty.<n>We propose a unified meta-budgetalgorithmic framework capable of operating under both fixed-confidence and fixed-optimal regimes.<n>Our approach outperforms existing methods in terms of both accuracy and sample efficiency.
  arXiv  Detail & Related papers  (2025-06-27T14:21:03Z)
• Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning [19.292214425524303]
  We study risk-sensitive reinforcement learning (RL), a crucial field due to its ability to enhance decision-making in scenarios where it is essential to manage uncertainty and minimize potential adverse outcomes. Our work focuses on applying the entropic risk measure to RL problems. We center on the linear Markov Decision Process (MDP) setting, a well-regarded theoretical framework that has yet to be examined from a risk-sensitive standpoint.
  arXiv  Detail & Related papers  (2024-07-10T13:09:52Z)
• A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents [44.09686403685058]
  We study risk-sensitive RL where the goal is learn a history-dependent policy that optimize some risk measure of cumulative rewards.<n>We propose two meta-algorithms: one grounded in optimism and another based on policy gradients.<n>We empirically show that our algorithms learn the optimal history-dependent policy in a proof-of-concept MDP.
  arXiv  Detail & Related papers  (2024-03-10T21:45:12Z)
• Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation [54.61816424792866]
  We introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. We design two innovative meta-algorithms: textttRS-DisRL-M, a model-based strategy for model-based function approximation, and textttRS-DisRL-V, a model-free approach for general value function approximation.
  arXiv  Detail & Related papers  (2024-02-28T08:43:18Z)
• Risk-Aware Reinforcement Learning through Optimal Transport Theory [4.8951183832371]
  This paper pioneers the integration of Optimal Transport theory with reinforcement learning (RL) to create a risk-aware framework. Our approach modifies the objective function, ensuring that the resulting policy not only maximizes expected rewards but also respects risk constraints dictated by OT distances. Our contributions are substantiated with a series of theorems, mapping the relationships between risk distributions, optimal value functions, and policy behaviors.
  arXiv  Detail & Related papers  (2023-09-12T13:55:01Z)
• Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback [57.6775169085215]
  Risk-sensitive reinforcement learning aims to optimize policies that balance the expected reward and risk. We present a novel framework that employs an Iterated Conditional Value-at-Risk (CVaR) objective under both linear and general function approximations. We propose provably sample-efficient algorithms for this Iterated CVaR RL and provide rigorous theoretical analysis.
  arXiv  Detail & Related papers  (2023-07-06T08:14:54Z)
• Uniform Pessimistic Risk and its Optimal Portfolio [0.6445605125467574]
  We propose an integral of $alpha$-risk called the textituniform pessimistic risk and a computational algorithm to obtain an optimal portfolio based on the risk. Real data analysis of three stock datasets (S&P500, CSI500, KOSPI200) demonstrates the usefulness of the proposed risk and portfolio model.
  arXiv  Detail & Related papers  (2023-03-02T09:41:15Z)
• Efficient Risk-Averse Reinforcement Learning [79.61412643761034]
  In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. We prove that under certain conditions this inevitably leads to a local-optimum barrier, and propose a soft risk mechanism to bypass it. We demonstrate improved risk aversion in maze navigation, autonomous driving, and resource allocation benchmarks.
  arXiv  Detail & Related papers  (2022-05-10T19:40:52Z)
• Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO [66.5384483339413]
  We present a new monotonic improvement guarantee for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL) We show that a trust region constraint can be effectively enforced in a principled way by bounding independent ratios based on the number of agents in training.
  arXiv  Detail & Related papers  (2022-01-31T20:39:48Z)
• 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)

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.