Free Information Center
Exploration by random network distillation (RND) is a technique in reinforcement learning used to encourage agents to explore unfamiliar states by providing intrinsic rewards based on the novelty of observations. It leverages a fixed random neural network and a trainable network to measure prediction error as a proxy for novelty.
Curiosity-driven reinforcement learning is a subfield of reinforcement learning that incorporates intrinsic motivation mechanisms, encouraging agents to explore their environment beyond external rewards. This approach aims to improve learning efficiency in complex or sparse reward settings by fostering exploration through curiosity.
Curiosity-driven exploration refers to the pursuit of knowledge and understanding motivated primarily by curiosity rather than external rewards.
Random network distillation (RND) is a method in reinforcement learning that enhances exploration by utilizing a neural network’s output as a reward signal.