Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes

• URL: http://arxiv.org/abs/2607.12924v2
• Date: Wed, 15 Jul 2026 08:26:39 GMT
• Title: Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
• Abstract summary: We study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters.<n>In such settings Reinforcement Learning algorithms typically determine parameters with one-shot estimators, which makes their training sample inefficient.<n>We step into this gap and propose our novel Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL) algorithm.
• Score: 0.6308539010172308
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot estimators, which makes their training sample inefficient. Though in most PAMDP environments explicit but incomplete knowledge (e.g., rules, safety constraints, or expert heuristics) is available, it is rarely directly used to increase the sample-efficiency of training Reinforcement Learning agents. We step into this gap and propose our novel Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL) algorithm. KGRL uses domain knowledge in a Datalog knowledge base to derive the set of applicable actions and feasible parameters for a given state. This allows it to prune non-applicable actions from the decision-space and constrain the parameter spaces of the remaining actions. We then use a gradient-based parameter refinement loop to estimate the optimal parameters during training and deployment of the agent. By recording activated rules along the trajectory, KGRL additionally provides local procedural explanations on the pruning of actions and constraining of parameters. Overall, KGRL guides the agent's exploration and deployment toward feasible and constraint-aware decisions, while increasing sample efficiency during training. KGRL outperforms state-of-the-art RL baselines for PAMDPs in both, sample efficiency and episodic return.

Related papers

• Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions [10.407094497818436]
  Forward-Forward (FF) is a proposed learning procedure for neural networks that employs two forward passes instead of the traditional forward and backward passes used in backpropagation.<n>We introduce Action-conditioned Root mean squared Q-Functions (ARQ), a novel value estimation method that applies a goodness function and action conditioning for local RL.<n>Our approach achieves superior performance compared to state-of-the-art local backprop-free RL methods in the MinAtar and the DeepMind Control Suite benchmarks.
  arXiv  Detail & Related papers  (2025-10-08T05:06:09Z)
• A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning [0.6906005491572401]
  We propose a method for allocating expert numbers based on parameter sensitivity LoRA-SMoE.<n> Experimental results demonstrate that our LoRA-SMoE approach can enhance model performance while reducing the number of trainable parameters.
  arXiv  Detail & Related papers  (2025-05-06T13:22:46Z)
• 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)
• Prompt-Tuning Decision Transformer with Preference Ranking [83.76329715043205]
  We propose the Prompt-Tuning DT algorithm to address challenges by using trajectory segments as prompts to guide RL agents in acquiring environmental information. Our approach involves randomly sampling a Gaussian distribution to fine-tune the elements of the prompt trajectory and using preference ranking function to find the optimization direction. Our work contributes to the advancement of prompt-tuning approaches in RL, providing a promising direction for optimizing large RL agents for specific preference tasks.
  arXiv  Detail & Related papers  (2023-05-16T17:49:04Z)
• Assessment of Reinforcement Learning Algorithms for Nuclear Power Plant Fuel Optimization [0.0]
  This work presents a first-of-a-kind approach to utilize deep RL to solve the loading pattern problem and could be leveraged for any engineering design optimization.
  arXiv  Detail & Related papers  (2023-05-09T23:51:24Z)
• Deep Black-Box Reinforcement Learning with Movement Primitives [15.184283143878488]
  We present a new algorithm for deep reinforcement learning (RL) It is based on differentiable trust region layers, a successful on-policy deep RL algorithm. We compare our ERL algorithm to state-of-the-art step-based algorithms in many complex simulated robotic control tasks.
  arXiv  Detail & Related papers  (2022-10-18T06:34:52Z)
• A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems [1.11412540857944]
  The proposed fuzzy nonlinear mapping as-signs each member of the action set to its probability of being chosen in the next step. A user tunable parameter is introduced to control the action selection policy, which determines the agent's greedy behavior. Simulation results indicate that including fuzzy logic within the reinforcement learning in the proposed manner improves the learning algorithm's convergence rate.
  arXiv  Detail & Related papers  (2021-06-13T20:41:29Z)
• A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces [53.47210316424326]
  KeRNS is an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes. We prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time.
  arXiv  Detail & Related papers  (2020-07-09T21:37:13Z)
• AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
  We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS) Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
  arXiv  Detail & Related papers  (2020-06-11T16:36:31Z)
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking [59.691919635037216]
  Policy evaluation is a key process in Reinforcement Learning (RL) We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties.
  arXiv  Detail & Related papers  (2020-02-17T13:30:43Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

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.