Reinforcement learning agents solve complex tasks without access to the reward function by training a reward predictor from human comparisons of trajectory segments, requiring feedback on less than 1% of interactions.
A bayesian interactive optimization approach to procedural animation design
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2017 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Deep reinforcement learning from human preferences
Reinforcement learning agents solve complex tasks without access to the reward function by training a reward predictor from human comparisons of trajectory segments, requiring feedback on less than 1% of interactions.