all AI news
Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance. (arXiv:2206.03787v2 [cs.LG] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Many Deep Reinforcement Learning (D-RL) algorithms rely on simple forms of
exploration such as the additive action noise often used in continuous control
domains. Typically, the scaling factor of this action noise is chosen as a
hyper-parameter and is kept constant during training. In this paper, we focus
on action noise in off-policy deep reinforcement learning for continuous
control. We analyze how the learned policy is impacted by the noise type, noise
scale, and impact scaling factor reduction schedule. We …
arxiv exploration impact learning lg noise performance policy reinforcement reinforcement learning