Search Results for author: Jasmina Gajcin

Found 5 papers, 3 papers with code

RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning

1 code implementation8 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.

reinforcement-learning Reinforcement Learning (RL)

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning

2 code implementations2 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.

Causal Inference reinforcement-learning +1

Counterfactual Explanations for Reinforcement Learning

no code implementations21 Oct 2022 Jasmina Gajcin, Ivana Dusparic

Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system.

reinforcement-learning Reinforcement Learning (RL)

ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning

1 code implementation21 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.

reinforcement-learning Reinforcement Learning (RL)

Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents

no code implementations17 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.

Autonomous Driving reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.