Effective Learning in Non-Stationary Multiagent Environments
Multiagent reinforcement learning (MARL) provides a principled framework for a group of artificial intelligence agents to learn collaborative and/or competitive behaviors at the level of human experts. Multiagent learning settings inherently solve much more complex problems than single-agent learnin...
Main Author: | Kim, Dong Ki |
---|---|
Other Authors: | How, Jonathan P. |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/150177 |
Similar Items
-
Learning to teach and meta-learning for sample-efficient multiagent reinforcement learning
by: Kim, Dong Ki(Aeronautics and astronautics scientist)Massachusetts Institute of Technology.
Published: (2020) -
Policy Distillation and Value Matching in Multiagent Reinforcement Learning
by: Wadhwania, Samir, et al.
Published: (2021) -
Learning to Teach in Cooperative Multiagent Reinforcement Learning
by: Omidshafie, Shayegan, et al.
Published: (2021) -
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
by: Kim, Dong-Ki, et al.
Published: (2022) -
Causal Inference: Heterogeneous Effects and Non-stationary Environments
by: Slavov, Stanislav
Published: (2022)