Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization

Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency constraints during the training, thus resulting in inefficient exploration in the early stage. In this paper, we propose an algorithm named Constrained Policy Optimization with Extra Safety Budget (ESB-CPO) to strike a balance between the exploration efficiency and the constraints satis-faction. In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety bud-get) with the aid of a new metric we propose. With the training process, the constraints in our optimization problem become tighter. Meanwhile, theoretical analysis and practical experiments demonstrate that our method gradually meets the cost limit's demand in the final training stage. When evaluated on Safety-Gym and Bullet-Safety-Gym benchmarks, our method has shown its advantages over baseline algorithms in terms of safety and optimality. Remarkably, our method gains remarkable performance improvement under the same cost limit compared with baselines.

Authors

• Haotian Xu
• Shengjie Wang
• Zhaolei Wang
• Yunzhe Zhang
• Qing Zhuo
• Yang Gao 0029
• Tao Zhang

Keywords

• Training
• Measurement
• Costs
• Estimation
• Reinforcement learning
• Stability analysis
• Safety
• Optimal Policy
• Constrained Optimization
• Constrained Policy Optimization
• Safety Budget
• Optimization Problem
• Robotic Tasks
• Constraint Satisfaction
• Consistency Constraint
• Value Function
• Lagrange Multiplier
• Stable Values
• Inequality Constraints
• Lyapunov Function
• Reward Function
• Markov Decision Process
• Sum Of Costs
• Interior Point Method
• Unconstrained Problem
• Safety Policies
• Practical Algorithm
• Trust Region
• Early Epoch
• Trust Region Method
• Safety Constraints
• Policy Update