MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning.
Bram GrootenTristan TomilinGautham VasanMatthew E. TaylorA. Rupam MahmoodMeng FangMykola PechenizkiyDecebal Constantin MocanuPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- learning tasks
- markov decision processes
- knowledge acquisition
- learning systems
- supervised learning
- learning agent
- temporal difference learning
- visual information
- state space
- markov decision process
- learning agents
- reinforcement learning methods
- eligibility traces