Graphical physics network integrated with DRL and intrinsic reward normalization lets an agent improve its intuitive physics model via intrinsic motivation in stationary and non-stationary 3D environments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization
Graphical physics network integrated with DRL and intrinsic reward normalization lets an agent improve its intuitive physics model via intrinsic motivation in stationary and non-stationary 3D environments.