Hypercube Policy Regularization Framework for Offline Reinforcement Learning

Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning methods cannot get satisfactory results in offline reinforcement learning due to the out-of-distribution state actions that the dataset cannot cover during training. To solve this problem, the policy regularization method that tries to directly clone policies used in static datasets has received numerous studies due to its simplicity and effectiveness. However, policy constraint methods make the agent choose the corresponding actions in the static dataset. This type of constraint is usually over-conservative, which results in suboptimal policies, especially in low-quality static datasets. In this paper, a hypercube policy regularization framework is proposed, this method alleviates the constraints of policy constraint methods by allowing the agent to explore the actions corresponding to similar states in the static dataset, which increases the effectiveness of algorithms in low-quality datasets. It was also theoretically demonstrated that the hypercube policy regularization framework can effectively improve the performance of original algorithms. In addition, the hypercube policy regularization framework is combined with TD3-BC and Diffusion-QL for experiments on D4RL datasets which are called TD3-BC-C and Diffusion-QL-C. The experimental results of the score demonstrate that TD3-BC-C and Diffusion-QL-C perform better than state-of-the-art algorithms like IQL, CQL, TD3-BC and Diffusion-QL in most D4RL environments in approximate time.

Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning

Offline reinforcement learning learns from a static dataset without interacting with the environment, which ensures security and thus owns a good prospect of application. However, directly applying naive reinforcement learning methods usually fails in an offline environment due to function approximation errors caused by out-of-distribution(OOD) actions. To solve this problem, existing algorithms mainly penalize the Q-value of OOD actions, the quality of whose constraints also matter. Imprecise constraints may lead to suboptimal solutions, while precise constraints require significant computational costs. In this paper, we propose a novel count-based method for continuous domains, called Grid-Mapping Pseudo-Count method(GPC), to penalize the Q-value appropriately and reduce the computational cost. The proposed method maps the state and action space to discrete space and constrains their Q-values through the pseudo-count. It is theoretically proved that only a few conditions are needed to obtain accurate uncertainty constraints in the proposed method. Moreover, we develop a Grid-Mapping Pseudo-Count Soft Actor-Critic(GPC-SAC) algorithm using GPC under the Soft Actor-Critic(SAC) framework to demonstrate the effectiveness of GPC. The experimental results on D4RL benchmark datasets show that GPC-SAC has better performance and less computational cost compared to other algorithms.