URNAI: A Multi-Game Toolkit for Experimenting Deep Reinforcement Learning Algorithms.
Marco A. S. AraùjoLuiz P. C. AlvesCharles A. G. MadeiraMarcos M. NóbregaPublished in: SBGames (2020)
Keyphrases
- reinforcement learning algorithms
- markov games
- stochastic games
- reinforcement learning
- markov decision processes
- state space
- model free
- reinforcement learning problems
- temporal difference
- eligibility traces
- multiagent reinforcement learning
- learning algorithm
- reward function
- game theory
- nash equilibrium
- function approximation
- dynamic environments
- reinforcement learning methods
- partially observable environments
- game playing
- function approximators
- policy iteration
- policy search
- optimal policy
- learning tasks
- supervised learning
- reward shaping
- machine learning
- game theoretic