Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer.
Yusen ZhanHaitham Bou-AmmarMatthew E. TaylorPublished in: IJCAI (2016)
Keyphrases
- reinforcement learning
- optimal policy
- learning environment
- learning process
- dynamic programming
- transfer learning
- positive and negative
- professional development
- e learning
- reward function
- reinforcement learning algorithms
- markov decision process
- control policies
- policy search
- learning experience
- markov decision processes
- learning activities
- learning scenarios
- state space
- function approximators
- reinforcement learning problems
- state and action spaces
- partially observable environments