Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

50101151201 · Jun 202019922001200920172026
48 results for Conservative Policy

Theoretical analysis confirms non-conservative algorithms can converge to optimal policies.

problem Theoretical guarantees for non-conservative reinforcement learning algorithms.
method Theoretical analysis of Peng's Q(λλ) algorithm.
result Peng's Q(λλ) converges to an optimal policy under certain conditions.

BCPO optimizes offline RL policies by converting uncertainty into conservative bounds.

problem Offline RL's fragility under distribution shifts and model errors.
method Bayesian approach with credible lower bounds and KL regularization.
result BCPO yields an uncertainty-calibrated policy that avoids exploiting model errors.

HAMBO estimates policy performance by hallucinating worst-case trajectories, providing valid lower bounds.

problem Conservative off-policy evaluation of policies in real-world applications.
method HAMBO hallucinates worst-case trajectories based on learned model uncertainty.
result Valid lower bounds on policy performance, converging to true expected return under regular conditions.

Paper proposes an RL algorithm to ensure policy performance guarantees.

problem Lack of performance guarantees for RL policies compared to baselines.
method Online model-free algorithm that ensures conservative exploration.
result Regret bound of ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) for both discrete and continuous spaces.

StepMix algorithm ensures safe exploration in reinforcement learning with near-optimal performance.

problem Conservative exploration in reinforcement learning under episode-wise constraints.
method StepMix algorithm balances exploitation and exploration while ensuring episode-wise conservative constraint.
result StepMix achieves near-optimal regret order as in the constraint-free setting.

CQL learns conservative Q-functions to improve offline RL performance.

problem Leveraging large, static datasets in reinforcement learning without further interaction.
method Conservative Q-learning (CQL) which learns a conservative Q-function to lower-bound policy values.
result CQL substantially outperforms existing offline RL methods, often achieving 2-5 times higher final returns.

VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.

problem Optimizing VaR-constrained reinforcement learning problems.
method Combines Cantelli's inequality and trust-region framework for efficient and conservative optimization.
result Achieves zero constraint violations during training in feasible environments.

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will eventually learn a good or optimal policy, there is no guarantee on the quality of the in…

2020-02-08abs ↗pdf ↗

SCPO learns robust policies without modeling disturbance, improving real-world task performance.

problem Poor performance of reinforcement learning in real-world tasks due to disturbance in transition dynamics.
method State-conservative policy optimization (SCPO) that reduces disturbance to state space and approximates it with a gradient-based regularizer.
result SCPO learns robust policies without prior knowledge of disturbance or simulators, improving performance in robot control tasks.

The paper tackles safe exploration in RL by a conservative safety critic.

problem Safe exploration in reinforcement learning (RL) when partially trained policies are deployed.
method Learning a conservative safety estimate through a critic, provably bounding catastrophic failures.
result The approach provably converges to competitive task performance with significantly lower catastrophic failure rates.

Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.

problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.

In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often suboptimal. In this case, it is desirable to deploy online learning algorithms (e.g.,…

2020-02-08abs ↗pdf ↗

Paper presents a reduction-based framework for conservative bandits and RL with improved lower and upper bounds.

problem Conservative bandits and reinforcement learning problems.
method Reduction technique to calculate necessary and sufficient budget from baseline policy.
result Improved lower and upper bounds for various conservative settings.

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this pa…

2018-03-11abs ↗pdf ↗

Proposes a method to avoid excessive exploration in reinforcement learning.

problem Avoiding excessive exploration in reinforcement learning to deploy it in practice.
method Designs a novel algorithm using UCB reinforcement learning policy with adaptive exploration constraints.
result Proves that the approach remains conservative while minimizing regret in tabular settings and validates on real-world tasks.

Conservative Policy Iteration (CPI) is a founding algorithm of Approximate Dynamic Programming (ADP). Its core principle is to stabilize greediness through stochastic mixtures of consecutive policies. It comes with strong theoretical guarantees, and inspired approaches in deep Reinforcement Learning (RL). However, CPI …

2019-06-24abs ↗pdf ↗

Higher conservative training increases reward-hacking in reasoning models.

problem Reward hacking during online adaptation in reasoning models.
method Conservative offline training with varying levels of conservatism (β) was applied to a Qwen3-14B policy, and online adaptation was measured against a reward ensemble.
result Higher conservatism (β) increases reward-hacking damage, measured by the Goodhart gap and AUGC.

Proposes a method to improve few-shot transfer in off-dynamics RL.

problem Traditional RL struggles with transferring policies between environments with different dynamics.
method Introduces a penalty to regulate source-trained policies in target environments with limited data.
result Improves performance in various off-dynamics RL scenarios compared to existing methods.

New algorithms optimize a soft-robust criterion in reinforcement learning, reducing conservatism.

problem Computing robust policies for high-stakes decisions with limited data.
method Soft-robust criterion using risk measures, two algorithms for optimization.
result Our algorithms produce less conservative solutions than existing methods.

Develops a support-aware framework for reserve-policy selection in advertising markets.

problem Log-based reserve-price evaluation risks weak support and subgroup harm.
method Support-aware offline decision framework converting logged evidence into certified policies.
result Preserves the best gate-passing policy while eliminating only policies with certified regret.

Develops algorithms for CCBs with non-linear costs, improving safety and performance.

problem Safety constraints in sequential decision making with non-linear arm costs.
method Innovative algorithms using Inverse Gap Weighting (IGW) and online regression oracle.
result Sub-linear regret bounds for C-SquareCB and first-order regret for C-FastCB.

In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum degree that is the same at each state. This can cause batch RL to be overly conservat…

2020-02-08abs ↗pdf ↗

Paper proposes a new DRL algorithm optimizing Spectral Risk Measures for better risk management.

problem Inconsistencies and conservatism in existing risk measures in DRL.
method Optimizes a broader class of static Spectral Risk Measures (SRM) in DRL.
result Demonstrates improved performance over existing risk-neutral and risk-sensitive DRL models.

Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate policy evaluation followed by a softened policy improvement step. As so, they are…

2019-07-02abs ↗pdf ↗

New offline RL algorithms tackle partial data coverage with optimal performance and practicality.

problem Partial data coverage in offline RL datasets.
method Augmented Lagrangian method applied to MIS formulation for optimal offline RL.
result Statistically optimal offline RL with practical performance, eliminating conservatism.

New bounds assess policy evaluation under unobserved confounders, showing model-based methods are more effective.

problem Policy evaluation under unobserved confounders in uncertain causal environments.
method Developed worst-case bounds for sensitivity to unobserved confounders, demonstrating model-based methods are more effective.
result Model-based approaches with robust MDPs provide sharper lower bounds for policy evaluation.

EcoCast predicts biodiversity risks using satellite data and citizen science records.

problem Unprecedented shifts in species distributions due to climate change and habitat loss.
method Spatio-temporal model using sequence-based transformers and continual learning.
result Promising improvements in forecasting bird species distributions compared to Random Forest.

Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is det…

2018-11-15abs ↗pdf ↗

Study maps research streams in biodiversity finance, identifies key areas.

problem Biodiversity loss and need for finance to reverse trends.
method Quantitative bibliometric analysis of 189,456 references.
result Identifies eight primary research streams in biodiversity finance.

New RL algorithms learn policies competitive with best in class without assuming optimal policy.

problem Agnostic RL where best policy not necessarily optimal.
method First-order optimization in non-Euclidean space, reducing to policy learning.
result Sample complexity upper bounds for three algorithms under VGD condition.

Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this…

2019-07-11abs ↗pdf ↗

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as constrained Markov decision processes (CMDPs) and present safe p…

2019-01-28abs ↗pdf ↗