Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Feb-16-2026, 01:09:44 GMT–Neural Information Processing Systems

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies.

artificial intelligence, machine learning, reinforcement learning, (14 more...)

Neural Information Processing Systems

Feb-16-2026, 01:09:44 GMT

Conferences PDF

Country:
- Asia
  - China (0.04)
  - Macao (0.04)
- Europe
  - Germany > Hesse
    - Darmstadt Region > Darmstadt (0.04)
  - Switzerland > Basel-City
    - Basel (0.04)
- North America > United States
  - Arizona > Maricopa County
    - Phoenix (0.04)
  - California > San Francisco County
    - San Francisco (0.14)

Genre:
- Research Report
  - Experimental Study (1.00)
  - New Finding (0.67)

Industry:
- Leisure & Entertainment > Games (0.93)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Neural Networks > Deep Learning (0.46)
  - Reinforcement Learning (1.00)

Duplicate Docs Excel Report

Title
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Similar Docs Excel Report more

Title	Similarity	Source
None found