Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation.
Do June MinVerónica Pérez-RosasKenneth ResnicowRada MihalceaPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- eligibility traces
- reinforcement learning algorithms
- reward function
- average reward
- markov decision processes
- learning algorithm
- partially observable environments
- model free
- state space
- transfer learning
- optimal policy
- long run
- dynamic environments
- markov decision process
- learning process
- learning capabilities
- learning agent
- multi agent
- state action
- case study
- reward shaping
- robotic control
- genetic algorithm