Finding Mixed-Strategy Equilibria of Continuous-Action Games without Gradients Using Randomized Policy Networks.
Carlos MartinTuomas SandholmPublished in: IJCAI (2023)
Keyphrases
- mixed strategy
- pure strategy
- nash equilibrium
- nash equilibria
- continuous action
- policy search
- game theoretic
- game theory
- finite horizon
- incomplete information
- continuous state
- optimal policy
- partially observable markov decision processes
- stochastic games
- solution concepts
- reinforcement learning
- pure nash equilibria
- infinite horizon
- long run
- control policies
- evolutionary game theory
- reinforcement learning algorithms
- worst case
- lower bound