VfO trains a state-value function on action-free expert demonstrations mixed with lower-quality background data, then uses advantage-weighted regression on the background data to improve the agent, approaching oracle reward-based RL in several simulated tasks.
Title resolution pending
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
-
Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
VfO trains a state-value function on action-free expert demonstrations mixed with lower-quality background data, then uses advantage-weighted regression on the background data to improve the agent, approaching oracle reward-based RL in several simulated tasks.