Empirical study finds prior beliefs over policy types significantly impact long-term performance in multiagent learning, with effects scaling by planning horizon depth, and automatic priors achieve consistent results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types
Empirical study finds prior beliefs over policy types significantly impact long-term performance in multiagent learning, with effects scaling by planning horizon depth, and automatic priors achieve consistent results.