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.
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates,
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.