Convergent multiple-timescales reinforcement learning algorithms in normal form games
From MaRDI portal
Publication:1429103
DOI10.1214/aoap/1069786497zbMath1084.68102OpenAlexW2067018002MaRDI QIDQ1429103
E. J. Collins, David S. Leslie
Publication date: 30 March 2004
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://projecteuclid.org/euclid.aoap/1069786497
Learning and adaptive systems in artificial intelligence (68T05) (n)-person games, (n>2) (91A06) Stochastic approximation (62L20) Multistage and repeated games (91A20)
Related Items (8)
A note on adjusted replicator dynamics in iterated games ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ Online calibrated forecasts: memory efficiency versus universality for learning in games ⋮ Continuous-Time Convergence Rates in Potential and Monotone Games ⋮ Towards multi‐agent reinforcement learning‐driven over‐the‐counter market simulations ⋮ Weak convergence of dynamical systems in two timescales ⋮ Emergence of information transfer by inductive learning ⋮ Generalised weakened fictitious play
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Nonconvergence to unstable points in urn models and stochastic approximations
- Stochastic approximation methods for constrained and unconstrained systems
- Learning mixed equilibria
- Three problems in learning mixed-strategy Nash equilibria
- Stochastic approximation with two time scales
- Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
- A note on best response dynamics.
- Learning in perturbed asymmetric games
- Games with randomly disturbed payoffs: a new rationale for mixed-strategy equilibrium points
- Non-cooperative games
- The allocation of offensive and defensive resources in a territorial game
- REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES
- Actor-Critic--Type Learning Algorithms for Markov Decision Processes
This page was built for publication: Convergent multiple-timescales reinforcement learning algorithms in normal form games