BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning

• URL: http://arxiv.org/abs/2608.30283v1
• Date: Mon, 31 Aug 2026 05:52:29 GMT
• Title: BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning
• Abstract summary: We propose BCPPO (Bachelier-Inspired Constrained Proximal Policy Optimization) as a policy optimization (PPO) method.<n>Separately cost-prediction networks (critics) produce disagreement that marks predictions sensitive to which state-action regions occur in the training data.<n>A saturation-aware controller adjusts the mean-cost penalty and stops accumulated error from growing while that penalty is clipped.
• Score: 0.5461938536945722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Expected-cost constraints can still permit rare, high-cost events. Monte Carlo conditional value at risk (CVaR) gradients can be noisy at high confidence, whereas critics that model an outcome distribution add complexity. We propose BCPPO (Bachelier-Inspired Constrained Proximal Policy Optimization), a proximal policy optimization (PPO) method. Separately initialized cost-prediction networks (critics), trained with random sample masks, produce disagreement that marks predictions sensitive to which state-action regions occur in the training data and to critic training. A Bachelier formula for the expected amount above a reference level converts this disagreement into a smooth policy-update penalty. Gradients from this penalty do not alter the critics, so temporal-difference (TD) critic learning is unchanged. A saturation-aware controller adjusts the mean-cost penalty and stops accumulated error from growing while that penalty is clipped. Deployment retains only the policy network. The disagreement penalty is neither a tail-event probability nor a guaranteed error bound, and it provides no safety guarantee. Across 175 runs with shared tasks, costs, budgets, training steps, and evaluation seeds, no comparator attains both higher mean return and lower mean CVaR than BCPPO in any task. On Push1, BCPPO has no lower return and no higher CVaR than every comparator, with at least one strict gain. These results support a practical balance among reward, caution around cost predictions that vary across trained critics, and policy-only deployment.

Related papers

• Counterfactual Shapley Credit Assignment [49.39649767581182]
  Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents.<n>We introduce Counterfactual Shapley Credit Assignment, a novel framework that attributes credit and blame via the Counterfactual Shapley ($$-value)<n>We derive a consistent estimator that computes $$$-values, enabling a new class of policy methods, $$-PPO, combined with Prioritized Trajectory Replay (PTR)
  arXiv  Detail & Related papers  (2026-07-18T23:28:20Z)
• VIMPO: Value-Implicit Policy Optimization for LLMs [106.88933849641272]
  Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token.<n>Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability.<n>We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from optimality conditions of KL-regularized reinforcement learning.
  arXiv  Detail & Related papers  (2026-06-18T09:44:12Z)
• EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training [69.32453275232662]
  We show that a learned critic can inject estimation noise that exceeds the state signal it captures, increasing rather than reducing advantage variance.<n>We propose Explained Variance Policy Optimization (EVPO), which monitors batch-level EV at each training step and adaptively switches between critic-based and batch-mean advantage estimation.
  arXiv  Detail & Related papers  (2026-04-21T14:07:39Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds [1.2183405753834562]
  offline reinforcement learning (RL) aims to learn decision policies from a fixed batch of logged transitions.<n>We propose emphBayesian Conservative Policy Optimization (BCPO), a unified framework that converts uncertainty into emphprovably conservative policy improvement.<n>BCPO maintains a hierarchical Bayesian posterior over environment/value models, constructs a emphcredible lower bound (LCB) on action values, and performs policy updates under explicit KL regularization.
  arXiv  Detail & Related papers  (2026-03-06T01:46:02Z)
• Mitigating Mismatch within Reference-based Preference Optimization [55.07698254211876]
  Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models.<n>DPO weighs each update relative to a reference, which stabilizes the training by regularizing the updates within a trusted region.<n>This reliance becomes problematic for pessimistic pairs, where the reference model prefers the rejected response.<n>We modify DPO to treat the reference as neutral when it is pessimistic by replacing $_-_mathrmref$ with $_-max0,_mathrmref$.
  arXiv  Detail & Related papers  (2026-02-12T12:55:51Z)
• Distributionally Robust Policy Learning under Concept Drifts [33.44768994272614]
  This paper studies a more nuanced problem -- robust policy learning under the concept drift.<n>We first provide a doubly-robust estimator for evaluating the worst-case average reward of a given policy.<n>We then propose a learning algorithm that outputs the policy maximizing the estimated policy value within a given policy class.
  arXiv  Detail & Related papers  (2024-12-18T19:53:56Z)
• Verifiably Robust Conformal Prediction [1.391198481393699]
  This paper introduces VRCP (Verifiably Robust Conformal Prediction), a new framework that leverages neural network verification methods to recover coverage guarantees under adversarial attacks. Our method is the first to support perturbations bounded by arbitrary norms including $ell1$, $ell2$, and $ellinfty$, as well as regression tasks. In every case, VRCP achieves above nominal coverage and yields significantly more efficient and informative prediction regions than the SotA.
  arXiv  Detail & Related papers  (2024-05-29T09:50:43Z)
• Off-Policy Primal-Dual Safe Reinforcement Learning [16.918188277722503]
  We show that the error in cumulative cost estimation causes significant underestimation of cost when using off-policy methods. We propose conservative policy optimization, which learns a policy in a constraint-satisfying area by considering the uncertainty in estimation. We then introduce local policy convexification to help eliminate such suboptimality by gradually reducing the estimation uncertainty.
  arXiv  Detail & Related papers  (2024-01-26T10:33:38Z)
• Correcting discount-factor mismatch in on-policy policy gradient methods [2.9005223064604078]
  We introduce a novel distribution correction to account for the discounted stationary distribution. Our algorithm consistently matches or exceeds the original performance on several OpenAI gym and DeepMind suite benchmarks.
  arXiv  Detail & Related papers  (2023-06-23T04:10:58Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)

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.