Approximate information state based convergence analysis of recurrent Q-learning

no code implementations • 9 Jun 2023 • Erfan Seyedsalehi, Nima Akbarzadeh, Amit Sinha, Aditya Mahajan

In spite of the large literature on reinforcement learning (RL) algorithms for partially observable Markov decision processes (POMDPs), a complete theoretical understanding is still lacking.

Q-Learning Reinforcement Learning (RL)

Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning

no code implementations • 6 Feb 2023 • Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan, Sarath Chandar

In our proposed method, when one agent updates its policy, other agents are allowed to update their policies as well, but at a slower rate.

Approximate information state for approximate planning and reinforcement learning in partially observed systems

1 code implementation • 17 Oct 2020 • Jayakumar Subramanian, Amit Sinha, Raihan Seraj, Aditya Mahajan

Our key result is to show that if a function of the history (called approximate information state (AIS)) approximately satisfies the properties of the information state, then there is a corresponding approximate dynamic program.

reinforcement-learning Reinforcement Learning (RL)