An RL agent trained with self-imagination and Theory-of-Mind intrinsic rewards balances its own task, rescuing others, and avoiding side effects in a small grid world.
Neuron 76(4), 677–694 (2012)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Autonomous Alignment with Human Value on Altruism through Considerate Self-imagination and Theory of Mind
An RL agent trained with self-imagination and Theory-of-Mind intrinsic rewards balances its own task, rescuing others, and avoiding side effects in a small grid world.