RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning.
Jasmina GajcinIvana DusparicPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- multi agent reinforcement learning
- function approximation
- markov decision processes
- temporal difference
- direct policy search
- state space
- learning process
- model free
- logical framework
- case study
- relational reinforcement learning
- learning algorithm
- multi agent
- reinforcement learning methods
- initial state
- policy search
- transition model
- temporal difference learning
- learning agents
- real robot
- partially observable
- action selection
- evolutionary algorithm
- optimal policy