Dynamic Reinforcement Learning For Actors

Abstract

Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in reinforcement learning (RL) from static to dynamic. The actor is initially designed to generate chaotic dynamics through the loop with its environment, enabling the agent to perform flexible and deterministic exploration. Dynamic RL controls global system dynamics using a local index called "sensitivity," which indicates how much the input neighborhood contracts or expands into the corresponding output neighborhood through each neuron's processing. While sensitivity adjustment learning (SAL) prevents excessive convergence of the dynamics, sensitivity-controlled reinforcement learning (SRL) adjusts them -- to converge more to improve reproducibility around better state transitions with positive TD error and to diverge more to enhance exploration around worse tran

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshibata2025dynamic

Related papers

• Population-coding And Dynamic-neurons Improved Spiking Actor Network For Reinforcement Learning (2021)0.00
• Broad Critic Deep Actor Reinforcement Learning For Continuous Control (2024)0.00
• Efficient Exploration In Deep Reinforcement Learning: A Novel Bayesian Actor-critic Algorithm (2024)0.00
• Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, And Decision Concepts (2022)0.00
• SALSA-RL: Stability Analysis In The Latent Space Of Actions For Reinforcement Learning (2025)0.00
• Dynamic Sparse Training For Deep Reinforcement Learning (2021)0.00
• Demystifying Reinforcement Learning In Time-varying Systems (2022)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00