Risk-Aware Constrained Reinforcement Learning with Non-Stationary Policies.
Zhaoxing YangHaiming JinYao TangGuiyun FanPublished in: AAMAS (2024)
Keyphrases
- non stationary
- reinforcement learning
- optimal policy
- policy search
- reinforcement learning algorithms
- control policies
- reward function
- model free
- markov decision processes
- adaptive algorithms
- fitted q iteration
- markov decision process
- reinforcement learning agents
- markov decision problems
- risk management
- control policy
- partially observable markov decision processes
- function approximation
- state space
- temporal evolution
- temporal difference
- autoregressive
- learning algorithm
- data mining
- white noise
- optimal control
- policy iteration
- infinite horizon
- long run
- financial time series
- stock price
- concept drift
- multi component
- feature vectors
- change point detection