Curiosity in exploring chemical spaces: intrinsic rewards for molecular reinforcement learning.
Luca A. ThiedeMario KrennAkshatKumar NigamAlán Aspuru-GuzikPublished in: Mach. Learn. Sci. Technol. (2022)
Keyphrases
- reinforcement learning
- drug discovery
- chemical reactions
- markov decision processes
- virtual screening
- molecular level
- function approximation
- state space
- temporal difference
- optimal policy
- chemical reaction
- three dimensional
- optimal control
- model free
- reward function
- reinforcement learning algorithms
- multi agent
- dna computing
- molecular dynamics
- machine learning
- markov decision process
- geometric structure
- learning problems
- learning process
- learning algorithm
- hidden state
- partially observable
- multi agent reinforcement learning
- data mining
- reward shaping
- multiarmed bandit