Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms
This work addresses performance improvements in hard continuous control tasks for reinforcement learning practitioners, representing an incremental advancement over existing methods.
The paper tackles continuous control reinforcement learning by proposing Distributed Distributional DrQ, a model-free off-policy algorithm that uses distributed distributional DDPG as its backbone to improve performance in hard continuous control tasks through enhanced distributional value function expression and distributed actor policies.
Distributed Distributional DrQ is a model-free and off-policy RL algorithm for continuous control tasks based on the state and observation of the agent, which is an actor-critic method with the data-augmentation and the distributional perspective of critic value function. Aim to learn to control the agent and master some tasks in a high-dimensional continuous space. DrQ-v2 uses DDPG as the backbone and achieves out-performance in various continuous control tasks. Here Distributed Distributional DrQ uses Distributed Distributional DDPG as the backbone, and this modification aims to achieve better performance in some hard continuous control tasks through the better expression ability of distributional value function and distributed actor policies.