Where-to-Learn: Analytical Policy Gradient Directed Exploration for On-Policy Robotic Reinforcement Learning
Abstract
A directed exploration method uses analytical policy gradients from a differentiable dynamics model to provide task-aware physics-guided guidance, steering agents toward high-reward regions for faster and more effective policy learning in robotic control.
On-policy reinforcement learning (RL) algorithms have demonstrated great potential in robotic control, where effective exploration is crucial for efficient and high-quality policy learning. However, how to encourage the agent to explore the better trajectories efficiently remains a challenge. Most existing methods incentivize exploration by maximizing the policy entropy or encouraging novel state visiting regardless of the potential state value. We propose a new form of directed exploration that uses analytical policy gradients from a differentiable dynamics model to inject task-aware, physics-guided guidance, thereby steering the agent towards high-reward regions for accelerated and more effective policy learning.
Get this paper in your agent:
hf papers read 2603.27317 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper