Collaborative Reinforcement Learning Model for Sustainability of Cooperation in Sequential Social Dilemmas.
Ritwik ChaudhuriKushal MukherjeeRamasuri NarayanamRohith Dwarakanath VallamAyush KumarAntriksh MathurShweta GargSudhanshu SinghGyana R. ParijaPublished in: AAMAS (2019)
Keyphrases
- reinforcement learning
- multi agent
- long term
- computational model
- cooperative
- conceptual model
- prior knowledge
- neural network
- experimental data
- parameter estimation
- model free
- prediction model
- formal model
- knowledge sharing
- statistical model
- optimal policy
- multi agent systems
- objective function
- similarity measure
- e learning