Pages that link to "Item:Q4967518"
From MaRDI portal
The following pages link to Superhuman AI for heads-up no-limit poker: Libratus beats top professionals (Q4967518):
Displaying 19 items.
- Libratus (Q41007) (← links)
- Multi-agent reinforcement learning: a selective overview of theories and algorithms (Q2094040) (← links)
- World-class interpretable poker (Q2102358) (← links)
- Committing to correlated strategies with multiple leaders (Q2238721) (← links)
- A distributed algorithm to obtain repeated games equilibria with discounting (Q2284815) (← links)
- The Hanabi challenge: a new frontier for AI research (Q2302288) (← links)
- Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games (Q2303656) (← links)
- Computing Large Market Equilibria Using Abstractions (Q5031015) (← links)
- Align, then memorise: the dynamics of learning with feedback alignment* (Q5049525) (← links)
- Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning (Q5154749) (← links)
- Asymmetric Action Abstractions for Planning in Real-Time Strategy Games (Q5870509) (← links)
- Solving zero-sum one-sided partially observable stochastic games (Q6098841) (← links)
- Provably efficient reinforcement learning in decentralized general-sum Markov games (Q6159512) (← links)
- Fast convergence of optimistic gradient ascent in network zero-sum extensive form games (Q6164523) (← links)
- A framework for self-evolving computational material models inspired by deep learning (Q6495609) (← links)
- Simple uncoupled no-regret learning dynamics for extensive-form correlated equilibrium (Q6551257) (← links)
- HSVI can solve zero-sum partially observable stochastic games (Q6624522) (← links)
- The evolutionary dynamics of soft-max policy gradient in multi-agent settings (Q6658313) (← links)
- Automatically designing counterfactual regret minimization algorithms for solving imperfect-information games (Q6665709) (← links)
