Introduces multistep predecessor models for Dyna planning to mitigate value hallucination by avoiding real-state updates from simulated values.
Pygame L earning E nvironment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
Introduces multistep predecessor models for Dyna planning to mitigate value hallucination by avoiding real-state updates from simulated values.