Offline reinforcement learning with closed-form policy improvement operators
International Conference on Machine Learning, 2023•proceedings.mlr.press
Behavior constrained policy optimization has been demonstrated to be a successful
paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a
policy is trained to maximize a learned value function while constrained by the behavior
policy to avoid a significant distributional shift. In this paper, we propose our closed-form
policy improvement operators. We make a novel observation that the behavior constraint
naturally motivates the use of first-order Taylor approximation, leading to a linear …
paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a
policy is trained to maximize a learned value function while constrained by the behavior
policy to avoid a significant distributional shift. In this paper, we propose our closed-form
policy improvement operators. We make a novel observation that the behavior constraint
naturally motivates the use of first-order Taylor approximation, leading to a linear …
Abstract
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while constrained by the behavior policy to avoid a significant distributional shift. In this paper, we propose our closed-form policy improvement operators. We make a novel observation that the behavior constraint naturally motivates the use of first-order Taylor approximation, leading to a linear approximation of the policy objective. Additionally, as practical datasets are usually collected by heterogeneous policies, we model the behavior policies as a Gaussian Mixture and overcome the induced optimization difficulties by leveraging the LogSumExp’s lower bound and Jensen’s Inequality, giving rise to a closed-form policy improvement operator. We instantiate both one-step and iterative offline RL algorithms with our novel policy improvement operators and empirically demonstrate their effectiveness over state-of-the-art algorithms on the standard D4RL benchmark. Our code is available at https://cfpi-icml23. github. io/.
proceedings.mlr.press