Deep and symbolic RL agents fail to maintain performance on simplified versions of Atari training tasks, whereas humans adapt, revealing reliance on shortcuts.
The option-critic architecture
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Reinforcement Learning Agents are not even close to Human Intelligence
Deep and symbolic RL agents fail to maintain performance on simplified versions of Atari training tasks, whereas humans adapt, revealing reliance on shortcuts.