Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning.
Ziyang TangYihao FengQiang LiuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- transfer learning
- reinforcement learning algorithms
- function approximation
- state space
- eligibility traces
- reward function
- model free
- learning algorithm
- state action
- learning agent
- markov decision processes
- total reward
- temporal difference
- learning process
- previously learned
- temporal difference learning
- action space
- control problems
- machine learning
- multi agent
- partially observable environments
- optimal policy
- multi agent reinforcement learning
- markov decision problems
- state action space
- learning agents
- partially observable
- reinforcement learning methods
- agent learns
- action selection
- dynamic programming
- learning problems