Compression and Localization in Reinforcement Learning for ATARI Games.
Joel Ruben Antony MonizBarun PatraSarthak GargPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- linear value function approximation
- reinforcement learning problems
- function approximation
- reinforcement learning algorithms
- state space
- markov decision processes
- game theory
- model free
- nash equilibria
- temporal difference
- control problems
- game playing
- imperfect information
- action selection
- game theoretic
- optimal policy
- stochastic games
- reinforcement learning methods
- markov games
- machine learning
- nash equilibrium
- dynamic programming
- markov decision problems
- learning algorithm
- neural network
- optimal control
- convergence rate
- transfer learning
- supervised learning
- mobile robot
- temporal difference learning