The authors propose MPC-MFRL, which couples a TRPO policy with model predictive control and reports model-free-level scores with fewer samples on MuJoCo tasks.
Sample-efficient reinforcement learning with stochastic ensemble value expansion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Model-based Lookahead Reinforcement Learning
The authors propose MPC-MFRL, which couples a TRPO policy with model predictive control and reports model-free-level scores with fewer samples on MuJoCo tasks.