Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL.
Taku YamagataAhmed KhalilRaúl Santos-RodríguezPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- dynamic programming
- optimal policy
- state space
- function approximation
- reinforcement learning algorithms
- markov decision processes
- model free
- decision problems
- sequence alignment
- multi agent
- decision making
- action selection
- rl algorithms
- reinforcement learning methods
- decision rules
- optimal control
- policy iteration
- markov decision problems
- multi agent reinforcement learning
- linear programming
- continuous state spaces
- temporal difference learning
- real time
- continuous state
- exploration strategy
- continuous state and action spaces
- learning agent
- reward function
- temporal difference
- infinite horizon
- learning problems
- learning tasks
- fault diagnosis
- fuzzy logic
- control system
- neural network