Risk-sensitive Actor-free Policy via Convex Optimization
This addresses safety concerns in reinforcement learning for applications where unintended consequences must be avoided, though it appears incremental as it builds on existing risk-sensitive methods.
The paper tackled the problem of safety in reinforcement learning by proposing an actor-free policy that optimizes a risk-sensitive criterion using conditional value at risk, with experimental results showing effective risk control.
Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensitive criterion based on the conditional value at risk. The risk-sensitive objective function is modeled using an input-convex neural network ensuring convexity with respect to the actions and enabling the identification of globally optimal actions through simple gradient-following methods. Experimental results demonstrate the efficacy of our approach in maintaining effective risk control.