A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022
Towards a generalized policy iteration theorem
We intend to advance the theoretical understanding of actor-critic algorithms under the lens of policy iteration.
论文与出版物
-
-
-
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms
Romain Laroche, Remi Tachet des Combes
AISTATS 2022 | March 2022
-
On the Chattering of SARSA with Linear Function Approximation
Shangtong Zhang, Romain Laroche, Remi Tachet des Combes
February 2022
arXiv | February 2022
-
-
-
Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates
Romain Laroche, Remi Tachet des Combes
NeurIPS 2021 | December 2021
-
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
October 2021
arXiv | October 2021
-
-
-
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022
-
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms
Romain Laroche, Remi Tachet des Combes
AISTATS 2022 | March 2022
-
On the Chattering of SARSA with Linear Function Approximation
Shangtong Zhang, Romain Laroche, Remi Tachet des Combes
February 2022
arXiv | February 2022
-
Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates
Romain Laroche, Remi Tachet des Combes
NeurIPS 2021 | December 2021
-
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
October 2021
arXiv | October 2021
-
-
-
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022
-
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms
Romain Laroche, Remi Tachet des Combes
AISTATS 2022 | March 2022
-
Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates
Romain Laroche, Remi Tachet des Combes
NeurIPS 2021 | December 2021
-
-
-
On the Chattering of SARSA with Linear Function Approximation
Shangtong Zhang, Romain Laroche, Remi Tachet des Combes
February 2022
arXiv | February 2022
-
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
October 2021
arXiv | October 2021
-