Adaptive Mimic: Deep Reinforcement Learning of Parameterized Bipedal Walking from Infeasible References.
Chong ZhangQi WuLiqian MaHongyuan SuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- data driven
- function approximation
- neural network
- case study
- artificial intelligence
- multi agent reinforcement learning
- denoising
- markov decision processes
- adaptive learning
- robotic control
- adaptive algorithms
- learning capabilities
- action selection
- reinforcement learning algorithms
- model free
- deep learning
- search space
- reinforcement learning methods
- multi agent
- information retrieval