Policy Certificates: Towards Accountable Reinforcement Learning.
Christoph DannLihong LiWei WeiEmma BrunskillPublished in: ICML (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- reinforcement learning problems
- control policy
- markov decision processes
- state and action spaces
- partially observable environments
- reinforcement learning algorithms
- policy gradient
- markov decision problems
- state space
- function approximators
- action space
- partially observable
- control policies
- partially observable markov decision processes
- approximate dynamic programming
- policy iteration
- actor critic
- policy evaluation
- function approximation
- continuous state
- model free reinforcement learning
- reward function
- partially observable domains
- rl algorithms
- state action
- temporal difference
- learning algorithm
- approximate policy iteration
- multi agent
- control problems
- agent receives
- robotic control
- learning process
- access control
- inverse reinforcement learning
- transfer learning
- model free
- infinite horizon
- continuous state spaces
- multi agent reinforcement learning
- optimal control