Search Results for author:
Found 5 papers, 3 papers with code
RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning
In this work, we propose RACCER, the first RL-specific approach to generating counterfactual explanations for the behaviour of RL agents.
Causal Counterfactuals for Improving the Robustness of Reinforcement Learning
Causal Curiosity provides an approach for using interventions, and CoPhy is modified to enable the RL agent to perform counterfactuals.
Counterfactual Explanations for Reinforcement Learning
Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system.
ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning
We propose ReCCoVER, an algorithm which detects causal confusion in agent's reasoning before deployment, by executing its policy in alternative environments where certain correlations between features do not hold.
Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents
In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function.
