Skip to content
conftrace_

policy gradient

651 papers

PG

Papers

Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021 Meta-Reinforcement Learning by Tracking Task Non-stationarity IJCAI 2021 Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment ICML 2021 Neural optimal feedback control with local learning rules NeurIPS 2021 Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling AAAI 2021 Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret ICML 2021 On-Policy Deep Reinforcement Learning for the Average-Reward Criterion ICML 2021 On Proximal Policy Optimization’s Heavy-tailed Gradients ICML 2021 On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method NeurIPS 2021 On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning NeurIPS 2021 On the Linear Convergence of Policy Gradient Methods for Finite MDPs AISTATS 2021 On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift JMLR 2021 Phasic Policy Gradient ICML 2021 Policy Gradient Bayesian Robust Optimization for Imitation Learning ICML 2021 Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods ICML 2021 Reinforced Attention for Few-Shot Learning and Beyond CVPR 2021 Reinforcement Based Learning on Classification Task Yields Better Generalization and Adversarial Accuracy (Student Abstract) AAAI 2021 Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation NAACL 2021 Robust Asymmetric Learning in POMDPs ICML 2021 Robust Policy Gradient against Strong Data Corruption ICML 2021 Robust Reinforcement Learning: A Constrained Game-theoretic Approach L4DC 2021 Robust Reinforcement Learning on State Observations with Learned Optimal Adversary ICLR 2021 Safe Pontryagin Differentiable Programming NeurIPS 2021 Sample Complexity of Policy Gradient Finding Second-Order Stationary Points AAAI 2021 Sample Efficient Reinforcement Learning with REINFORCE AAAI 2021