← authors · overview

• Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
  2023 · 7 citations
• Adaptive Rational Activations to Boost Deep Reinforcement Learning
  2021 · 2 citations
• Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
  2024 · 2 citations
• OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
  2023 · 1 citations
• LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
  2026
• GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
  2026
• Boosting deep Reinforcement Learning using pretraining with Logical Options
  2026
• Deep Reinforcement Learning Agents are not even close to Human Intelligence
  2025
• Deep Reinforcement Learning via Object-Centric Attention
  2025
• Better Decisions through the Right Causal World Model
  2025