2021 · 13 citations · 17 references
ComputingAutonomous SystemsMachine LearningMarkov Decision ProcessesRobot LearningGoal PlanningPolicy ImprovementPolicy LearningReinforcement LearningReinforcement Learning FoundationsDynamics Model LearningGoal InferenceModel-based Policy OptimizationPolicy OptimizationReinforcement Learning With Learned DynamicsSample EfficiencySample-efficient Policy LearningSparsity Problem
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In this paper, to enhance the diversity of relabeled goals, we develop FGI (Foresight Goal Inference), a new relabeling strategy that relabels the goals by looking into the future with a learned dynamics model. Besides, to improve sample efficiency, we propose to use the dynamics model to generate simulated trajectories for policy training. By integrating these two improvements, we introduce the MapGo framework (Model-Assisted Policy optimization for Goal-oriented tasks). In our experiments, we first show the effectiveness of the FGI strategy compared with the hindsight one, and then show that the MapGo framework achieves higher sample efficiency when compared to model-free baselines on a set of complicated tasks.
17
Continuous control with deep reinforcement learning
Timothy Lillicrap, Jonathan J. Hunt, Alexander Pritzel et al. · arXiv (Cornell University) · 2016 · 6.8K citations · Full text
Computing, Computer Science, Physics +17
Universal Value Function Approximators
Tom Schaul, Daniel Horgan, Karol Gregor et al. · 2015 · 616 citations
Benchmarking Model-Based Reinforcement Learning
Tingwu Wang, Xuchan Bao, Ignasi Clavera et al. · arXiv (Cornell University) · 2019 · 242 citations · Full text