Search Results for author: Jasmina Gajcin

Found 7 papers, 4 papers with code

ACTER: Diverse and Actionable Counterfactual Sequences for Explaining and Diagnosing RL Policies

no code implementations9 Feb 2024 Jasmina Gajcin, Ivana Dusparic

In this work, we propose ACTER (Actionable Counterfactual Sequences for Explaining Reinforcement Learning Outcomes), an algorithm for generating counterfactual sequences that provides actionable advice on how failure can be avoided.

counterfactual Counterfactual Reasoning +3

Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification

1 code implementation30 Aug 2023 Jasmina Gajcin, James McCarthy, Rahul Nair, Radu Marinescu, Elizabeth Daly, Ivana Dusparic

Our approach allows the user to provide trajectory-level feedback on agent's behavior during training, which can be integrated as a reward shaping signal in the following training iteration.

Reinforcement Learning (RL)

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 behavior of RL agents.

counterfactual reinforcement-learning +1

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning

2 code implementations2 Nov 2022 Tom He, Jasmina Gajcin, Ivana Dusparic

We apply CausalCF to complex robotic tasks and show that it improves the RL agent's robustness using CausalWorld.

Causal Inference reinforcement-learning +2

Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities

no code implementations21 Oct 2022 Jasmina Gajcin, Ivana Dusparic

Additionally, we explore the differences between counterfactual explanations in supervised learning and RL and identify the main challenges that prevent the adoption of methods from supervised in reinforcement learning.

counterfactual reinforcement-learning +1

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.

feature selection reinforcement-learning +1

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.