Probe classifiers can decode an RL agent's position from its LSTM activations in MiniHack, but this supports spatial information encoding, not a world model or self model.
Consciousness: An overview of the phe- nomenon and of its possible neural basis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Probing for Consciousness in Machines
Probe classifiers can decode an RL agent's position from its LSTM activations in MiniHack, but this supports spatial information encoding, not a world model or self model.