A Policy Gradient Algorithm for the Risk-Sensitive Exponential Cost MDP
We study the risk-sensitive exponential cost MDP formulation and develop a trajectory-based gradient algorithm to find the stationary point of the cost associated with a set of parameterized policies. We derive a formula that can be used to compute the policy gradient from (state, action, cost) information collected from sample paths of the MDP for each fixed parameterized policy. Unlike the traditional average-cost problem, standard stochastic approximation theory cannot be used to exploit this formula. To address the issue, we introduce a truncated and smooth version of the risk-sensitive cost and show that this new cost criterion can be used to approximate the risk-sensitive cost and its gradient uniformly under some mild assumptions. We then develop a trajectory-based gradient algorithm to minimize the smooth truncated estimation of the risk-sensitive cost and derive conditions under which a sequence of truncations can be used to solve the original, untruncated cost problem.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Risk-Sensitive Exponential Actor Critic
Model-free deep reinforcement learning (RL) algorithms have achieved tremendous success on a range of challenging tasks. However, safety concerns remain when these methods are deployed on real-world applications, necessi…
Reinforcement LearningRisk-Sensitive Reinforcement Learning via Policy Gradient Search
The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis
Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL framewo…
Policy Gradient MethodsReinforcement Learning (RL)Robot NavigationRisk-Sensitive Reinforcement Learning with Exponential Criteria
While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variance in the total rewar…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes
Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cos…
Computational Efficiency