paper-with-me

Papers

A Convergent Off-Policy Temporal Difference Algorithm

2019-11-13 · Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi, Shalabh Bhatnagar

Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of off-policy prediction. Temporal Difference (TD) learning algorithms are a popular class of algorithms for solving the prediction problem. TD algorithms with linear function approximation are shown to be convergent when the samples are generated from the target policy (known as on-policy prediction). However, it has been well established in the literature that off-policy TD algorithms under linear function approximation diverge. In this work, we propose a convergent on-line off-policy TD algorithm under linear function approximation. The main idea is to penalize the updates of the algorithm in a way as to ensure convergence of the iterates. We provide a convergence analysis of our algorithm. Through numerical evaluations, we further demonstrate the effectiveness of our algorithm.

📄 PDF Abstract BibTeX arXiv:1911.05697

Code (1)

raghudiddigi/Off-Policy-Convergent-Algorithm 공식 구현

Tasks

PredictionReinforcement LearningReinforcement Learning (RL)

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

On a convergent off -policy temporal difference learning algorithm in on-line learning environment

2016-05-19 · Prasenjit Karmakar, Rajkumar Maity, Shalabh Bhatnagar

In this paper we provide a rigorous convergence analysis of a "off"-policy temporal difference learning algorithm with linear function approximation and per time-step linear computational complexity in "online" learning …

A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation

2008-12-01 · NeurIPS 2008 12 · Richard S. Sutton, Hamid R. Maei, Csaba Szepesvári

We introduce the first temporal-difference learning algorithm that is stable with linear function approximation and off-policy training, for any finite Markov decision process, target policy, and exciting behavior policy…

Gradient Descent Temporal Difference-difference Learning

2022-09-10 · Rong J. B. Zhu, James M. Murray

Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple…

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…