How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
Preprint
Abstract
Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the gradient of the critic with respect to input actions. However, instead of gradients, the critic is, typically, only trained to accurately predict expected returns, which, on their own, are useless for policy optimization. In this paper, we propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients, which explicitly learns the action-value gradient. MAGE backpropagates through the learned dynamics to compute gradient targets in temporal difference learning, leading to a critic tailored for policy improvement. On a set of MuJoCo continuous-control tasks, we demonstrate the efficiency of the algorithm in comparison to model-free and model-based state-of-the-art baselines.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Model-based policy gradients with parameter-based exploration by least-squares conditional density estimationNeural Networks, 2014
- Value-gradient learning2012
- A Survey on Policy Search for RoboticsFoundations and Trends in Robotics, 2011
- Infinite-Horizon Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001
- Improving generalization performance using double backpropagationIEEE Transactions on Neural Networks, 1992