In navigation tasks, DQN learns MDP-homomorphism-invariant representations while PPO learns action-symmetric ones despite comparable performance, with effects on transfer and in LLMs.
Maslow’s hammer for catastrophic forgetting: Node re-use vs node activation.arXiv preprint arXiv:2205.09029, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
In navigation tasks, DQN learns MDP-homomorphism-invariant representations while PPO learns action-symmetric ones despite comparable performance, with effects on transfer and in LLMs.