Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations.
Ke SunYi LiuYingnan ZhaoHengshuai YaoShangling JuiLinglong KongPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- state space
- co occurrence
- multi agent reinforcement learning
- function approximation
- markov decision processes
- multi agent
- dynamic programming
- search space
- least squares
- transfer learning
- computational efficiency
- information retrieval
- evaluation function
- neural network
- noisy environments
- state transitions
- real time