Task-Agnostic Policy Distillation pretrains a continual RL agent with curiosity-driven exploration and policy distillation, yielding faster learning and higher scores on five Atari games.
Neural networks 113, 54–71 (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
Task-Agnostic Policy Distillation pretrains a continual RL agent with curiosity-driven exploration and policy distillation, yielding faster learning and higher scores on five Atari games.