Investigating the Effects of Hyperparameters in Quantum-Enhanced Deep Reinforcement Learning

Table 2

Some quantum-enhanced ML algorithms we found from the literary review.

Related works of literature	OpenAI gym environment		Performance	Algorithm used by the researcher
Yueh Hsiao et al. [30]		Acrobot and LunarLander	Converged faster	Proximal policy optimization (PPO)
Lockwood and Si [31]		CartPole-v1 and Acrobot	Not defined	Policy gradient with baseline’
Lan [32]		Pendulum	Faster convergency	Soft actor-critic
Yun et al. [33]		CartPole-v0	Not defined	Q-Learning
Hu and Hu [14]		2 × 3 frozen lakes	Not defined	Deep actor-critic