Double A3C: Deep Reinforcement Learning on OpenAI Gym Games.
Yangxin ZhongJiajie HeLingjie KongPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- action sets
- learning agents
- function approximation
- reinforcement learning agents
- game playing
- temporal difference learning
- computer games
- model free
- robotic control
- reinforcement learning algorithms
- game theoretic
- video games
- markov decision processes
- weighted majority
- optimal policy
- learning process
- stochastic games
- state space
- nash equilibria
- multiagent learning
- game design
- state abstraction
- game play
- educational games
- multi agent
- game theory
- game development
- perfect information
- supervised learning
- machine learning
- learning problems
- deep learning
- game tree search
- reinforcement learning methods
- coalitional games
- online game
- dynamic environments
- multi agent reinforcement learning
- temporal difference
- policy search
- virtual environment
- nash equilibrium
- learning algorithm