Risk-sensitive Actor-free Policy via Convex Optimization.
Ruoqi ZhangJens SjölundPublished in: CoRR (2023)
Keyphrases
- convex optimization
- risk sensitive
- control policies
- markov decision problems
- markov decision processes
- optimal control
- optimal policy
- utility function
- average cost
- infinite horizon
- model free
- control policy
- convex optimization problems
- decision theoretic
- policy iteration
- convex relaxation
- partially observable
- total variation
- linear programming
- markov decision process
- decision processes
- dynamic programming
- average reward
- optimality criterion
- state space
- reinforcement learning
- efficient optimization
- long run
- finite horizon
- multistage