paper-with-me

Papers

Neural Temporal-Difference and Q-Learning Provably Converge to Global Optima

2019-05-24 · NeurIPS 2019 12 · Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence of neural TD remains unclear. In this paper, we prove for the first time that neural TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation. In particular, we show how such global convergence is enabled by the overparametrization of neural networks, which also plays a vital role in the empirical success of neural TD. Beyond policy evaluation, we establish the global convergence of neural (soft) Q-learning, which is further connected to that of policy gradient algorithms.

📄 PDF Abstract BibTeX arXiv:1905.10027

Code (1)

water-bridge/2020rl pytorch

Tasks

Deep Reinforcement LearningQ-LearningReinforcement Learning

Similar Papers 제목 키워드 기반

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

2019-11-11 · ICML 2020 1 · Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained vi…

Vocal Bursts Valence Prediction

Neural Temporal-Difference Learning Converges to Global Optima

2019-12-01 · NeurIPS 2019 12 · Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coup…

Deep Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)

Gradient descent temporal difference-difference learning

2021-01-01 · Rong Zhu, James Murray

Off-policy learning algorithms, in which an agent updates the value function of the optimal policy while selecting actions using an independent exploration policy, provide an effective solution to the explore-exploit tra…

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

2023-05-08 · Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee

Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-age…

LEMMAMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory

2020-06-08 · Yufeng Zhang, Qi Cai, Zhuoran Yang, Yongxin Chen 외

Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. At the core of their empirical successes…

Deep Reinforcement LearningQ-Learning