1 code implementation • 8 Mar 2023 • Jasmina Gajcin, Ivana Dusparic
In this work, we propose RACCER, the first RL-specific approach to generating counterfactual explanations for the behaviour of RL agents.
2 code implementations • 2 Nov 2022 • Tom He, Jasmina Gajcin, Ivana Dusparic
Causal Curiosity provides an approach for using interventions, and CoPhy is modified to enable the RL agent to perform counterfactuals.
no code implementations • 21 Oct 2022 • Jasmina Gajcin, Ivana Dusparic
Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system.
1 code implementation • 21 Mar 2022 • Jasmina Gajcin, Ivana Dusparic
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.
no code implementations • 17 Dec 2021 • Jasmina Gajcin, Rahul Nair, Tejaswini Pedapati, Radu Marinescu, Elizabeth Daly, Ivana Dusparic
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.