Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
In offline reinforcement learning, the challenge of out-of-distribution (OOD) is pronounced. To address this, existing methods often constrain the learned policy through policy regularization. However, these methods often suffer from the issue of unnecessary conservativeness, hampering policy improvement. This occurs due to the indiscriminate use of all actions from the behavior policy that generates the offline dataset as constraints. The problem becomes particularly noticeable when the quality of the dataset is suboptimal. Thus, we propose Adaptive Advantage-guided Policy Regularization (A2PR), obtaining high-advantage actions from an augmented behavior policy combined with VAE to guide the learned policy. A2PR can select high-advantage actions that differ from those present in the dataset, while still effectively maintaining conservatism from OOD actions. This is achieved by harnessing the VAE capacity to generate samples matching the distribution of the data points. We theoretically prove that the improvement of the behavior policy is guaranteed. Besides, it effectively mitigates value overestimation with a bounded performance gap. Empirically, we conduct a series of experiments on the D4RL benchmark, where A2PR demonstrates state-of-the-art performance. Furthermore, experimental results on additional suboptimal mixed datasets reveal that A2PR exhibits superior performance. Code is available at https://github.com/ltlhuuu/A2PR.
Code (1)
Tasks
D4RLreinforcement-learningReinforcement LearningSimilar Papers 제목 키워드 기반
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all …
D4RLOffline RLReinforcement Learning (RL)Offline Reinforcement Learning with Adaptive Behavior Regularization
Offline reinforcement learning (RL) defines a sample-efficient learning paradigm, where a policy is learned from static and previously collected datasets without additional interaction with the environment. The major obs…
D4RLOffline RLreinforcement-learningReinforcement Learning+1Offline Reinforcement Learning with Soft Behavior Regularization
Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the poli…
continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value act…
Reinforcement LearningSupported Policy Optimization for Offline Reinforcement Learning
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elabo…
Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)