Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching

• URL: http://arxiv.org/abs/2601.10418v1
• Date: Thu, 15 Jan 2026 14:09:49 GMT
• Title: Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
• Authors: Nadav Merlis,
• Abstract summary: We study reinforcement learning problems with multiple steps of lookahead information.<n>Finding the optimal policy is NPhard, and it is common to apply one of two tractables: processing the lookahead in chunks of predefined sizes, and model predictive control.
• Score: 14.374726649836747
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent would reach and the rewards it would collect under any possible course of action. While it has been shown that such information can drastically boost the value, finding the optimal policy is NP-hard, and it is common to apply one of two tractable heuristics: processing the lookahead in chunks of predefined sizes ('fixed batching policies'), and model predictive control. We first illustrate the problems with these two approaches and propose utilizing the lookahead in adaptive (state-dependent) batches; we refer to such policies as adaptive batching policies (ABPs). We derive the optimal Bellman equations for these strategies and design an optimistic regret-minimizing algorithm that enables learning the optimal ABP when interacting with unknown environments. Our regret bounds are order-optimal up to a potential factor of the lookahead horizon $\ell$, which can usually be considered a small constant.

Related papers

• On the hardness of RL with Lookahead [34.030963310653874]
  We study reinforcement learning with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $ell$ actions before deciding its course of action.<n>While such information can drastically improve the achievable performance, we show that using this information optimally comes at a potentially prohibitive computational cost.
  arXiv  Detail & Related papers  (2025-10-22T08:47:18Z)
• Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization [42.2119634259269]
  Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly.<n>We propose the textbfDynamic Dual-Level Down-Sampling (D$3$S) framework that prioritizes the most informative samples and tokens across groups to improve the efficient of policy optimization.
  arXiv  Detail & Related papers  (2025-09-26T09:36:53Z)
• Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning [14.260168974085376]
  This paper investigates multi-objective reinforcement learning (MORL) It focuses on learning optimal policies in the presence of multiple reward functions. Despite MORL's success, there is still a lack of satisfactory understanding of various MORL optimization targets and efficient learning algorithms.
  arXiv  Detail & Related papers  (2024-07-24T17:58:49Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Offline Policy Optimization with Eligible Actions [34.4530766779594]
  offline policy optimization could have a large impact on many real-world decision-making problems. Importance sampling and its variants are a commonly used type of estimator in offline policy evaluation. We propose an algorithm to avoid this overfitting through a new per-state-neighborhood normalization constraint.
  arXiv  Detail & Related papers  (2022-07-01T19:18:15Z)
• Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation [107.54516740713969]
  We study human-in-the-loop reinforcement learning (RL) with trajectory preferences. Instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. We propose the first optimistic model-based algorithm for PbRL with general function approximation.
  arXiv  Detail & Related papers  (2022-05-23T09:03:24Z)
• Robust Predictable Control [149.71263296079388]
  We show that our method achieves much tighter compression than prior methods, achieving up to 5x higher reward than a standard information bottleneck. We also demonstrate that our method learns policies that are more robust and generalize better to new tasks.
  arXiv  Detail & Related papers  (2021-09-07T17:29:34Z)
• Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes [78.23907801786827]
  We introduce generalizations that ensure that our approach is both cost-aware and allows for fine-grained selection of examples through partially labeled scenes. Our experiments on a real-world, large-scale self-driving dataset suggest that fine-grained selection can improve the performance across perception, prediction, and downstream planning tasks.
  arXiv  Detail & Related papers  (2021-04-08T17:57:41Z)
• Deep Reinforcement Learning for Stock Portfolio Optimization [0.0]
  We will formulate the problem such that we can apply Reinforcement Learning for the task properly. To maintain a realistic assumption about the market, we will incorporate transaction cost and risk factor into the state as well. We will present the end-to-end solution for the task with Minimum Variance Portfolio for stock subset selection, and Wavelet Transform for extracting multi-frequency data pattern.
  arXiv  Detail & Related papers  (2020-12-09T10:19:12Z)
• DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning [95.60782037764928]
  We show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step. Third, we show that ideas in the propensity estimation literature can be used to importance-sample transitions from replay buffer and update policy to prevent deterioration of performance.
  arXiv  Detail & Related papers  (2020-06-26T20:21:12Z)
• Zeroth-Order Supervised Policy Improvement [94.0748002906652]
  Policy gradient (PG) algorithms have been widely used in reinforcement learning (RL) We propose Zeroth-Order Supervised Policy Improvement (ZOSPI) ZOSPI exploits the estimated value function $Q$ globally while preserving the local exploitation of the PG methods.
  arXiv  Detail & Related papers  (2020-06-11T16:49:23Z)

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.