S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics.
Samarth SinhaAjay MandlekarAnimesh GargPublished in: CoRL (2021)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- state space
- model free
- reinforcement learning algorithms
- learning algorithm
- artificial intelligence
- direct policy search
- multi agent
- temporal difference
- markov decision processes
- learning problems
- policy search methods
- learning classifier systems
- active learning
- machine learning
- optimal control
- real time
- learning capabilities
- rl algorithms
- computer vision