Offline Reinforcement Learning with Implicit Q-Learning.
Ilya KostrikovAshvin NairSergey LevinePublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- optimal policy
- state action space
- action selection
- multi agent reinforcement learning
- reinforcement learning methods
- markov decision processes
- real time
- learning agent
- learning algorithm
- approximate dynamic programming
- control problems
- eligibility traces
- temporal difference
- continuous state and action spaces
- supervised learning
- temporal difference learning
- learning process
- stochastic approximation
- neural network
- machine learning
- hierarchical reinforcement learning
- state abstraction
- multi agent
- learning classifier systems
- policy evaluation
- dynamic programming
- state action
- policy iteration
- transfer learning
- partially observable
- learning problems