Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments
Sign Up to like & getrecommendations! Published in 2021 at "Algorithms"
DOI: 10.3390/a14080226
Abstract: State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We… read more here.
Keywords: experience replay; deterministic environments; non deterministic; synthetic experiences ... See more keywords