Informed Initial Policies for Learning in Dec-POMDPs
By Landon Kraemer, Bikramjit Banerjee. 2012
8 citations recorded by the source corpus.
Decentralized partially observable Markov decision processes (Dec-POMDPs) offer a formal model for planning in cooperative multiagent systems where agents operate with noisy sensors and actuators, and local information. Prevalent Dec-POMDP solution techniques have mostly been centralized and have assumed knowledge of the model. In real world scenarios, however, solving centrally may not be an option and model parameters maybe unknown. To address this, we propose a distributed, model-free algorithm for learning Dec-POMDP policies, in which agents take turns learning, with each agent not currently learning following a static policy. For agents that have not yet learned a policy, this static policy must be initialized. We propose a principled method for learning such initial policies through interaction with the environment. We show that by using such informed initial policies, our alternate learning algorithm can find near-optimal policies for two benchmark problems.
Subfields: Artificial Intelligence, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jeremy Lyle
- Rajesh Yellamraju
- Landon Kraemer
- Bikramjit Banerjee
- Shimon Whiteson
- Tabish Rashid
- Gregory Farquhar
In Control and Systems Engineering
Citations in the corpus
- Multi-agent reinforcement learning as a rehearsal for decentralized planning (2016, neutral): “Furthermore, while an initialization phase for Q-Conc was studied in [14], it was unclear that this initialization improved results, thus we used default initialization.”
- Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs (2012, methodology): “See (Kraemer and Banerjee 2012) for more details.”