Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning

by   Wenjie Shi, et al.

Deep reinforcement learning (RL) agents are becoming increasingly proficient in a range of complex control tasks. However, the agent's behavior is usually difficult to interpret due to the introduction of black-box function, making it difficult to acquire the trust of users. Although there have been some interesting interpretation methods for vision-based RL, most of them cannot uncover temporal causal information, raising questions about their reliability. To address this problem, we present a temporal-spatial causal interpretation (TSCI) model to understand the agent's long-term behavior, which is essential for sequential decision-making. TSCI model builds on the formulation of temporal causality, which reflects the temporal causal relations between sequential observations and decisions of RL agent. Then a separate causal discovery network is employed to identify temporal-spatial causal features, which are constrained to satisfy the temporal causality. TSCI model is applicable to recurrent agents and can be used to discover causal features with high efficiency once trained. The empirical results show that TSCI model can produce high-resolution and sharp attention masks to highlight task-relevant temporal-spatial information that constitutes most evidence about how vision-based RL agents make sequential decisions. In addition, we further demonstrate that our method is able to provide valuable causal interpretations for vision-based RL agents from the temporal perspective.


page 6

page 7

page 8

page 9

page 10

page 11

page 12


Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning

Deep reinforcement learning (RL) has recently led to many breakthroughs ...

Causal policy ranking

Policies trained via reinforcement learning (RL) are often very complex ...

Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference

Although it is well known that exploration plays a key role in Reinforce...

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

We study a class of reinforcement learning (RL) tasks where the objectiv...

Global and Local Analysis of Interestingness for Competency-Aware Deep Reinforcement Learning

In recent years, advances in deep learning have resulted in a plethora o...

Structural Causal Interpretation Theorem

Human mental processes allow for qualitative reasoning about causality i...

Rethinking Causality-driven Robot Tool Segmentation with Temporal Constraints

Purpose: Vision-based robot tool segmentation plays a fundamental role i...

Please sign up or login with your details

Forgot password? Click here to reset