Deep RL agents with a log-compressed, scale-invariant memory (CogRNN) learn at similar rates across rescaled time intervals, unlike LSTM and RNN baselines.
Title resolution pending
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
-
Deep reinforcement learning with time-scale invariant memory
Deep RL agents with a log-compressed, scale-invariant memory (CogRNN) learn at similar rates across rescaled time intervals, unlike LSTM and RNN baselines.