Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning.
Abhishek GuptaVikash KumarCorey LynchSergey LevineKarol HausmanPublished in: CoRL (2019)
Keyphrases
- temporal difference
- reinforcement learning
- actor critic
- action selection
- sequential decision making
- function approximation
- temporal difference learning
- reinforcement learning algorithms
- policy evaluation
- optimal policy
- transfer learning
- supervised learning
- markov decision problems
- learning algorithm
- solve complex tasks
- eligibility traces
- evaluation function
- policy search
- reinforcement learning problems
- learning tasks
- reinforcement learning methods
- multi agent
- continuous state
- imitation learning
- learning process
- markov decision processes
- partially observable
- state action
- action space
- policy gradient methods
- learning problems
- optimal control
- state and action spaces
- partially observable environments
- model free reinforcement learning
- solving problems
- learning agents
- learning classifier systems
- online learning
- continuous state spaces
- autonomous robots