mlsanityData to 14 Oct 2026

Intrinsic Vicarious Conditioning for Deep Reinforcement Learning

arXiv 2605.12224 ↗First posted 12 May 2026cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by restricting how they learn from the environment as well as from others. Off-policy or learn-by-example methods can learn from demonstrators' representations, but they require access to the demonstrating agent's policies or their reward functions. Our work overcomes this direct sampling limitation by introducing vicarious conditioning as an intrinsic reward mechanism. We draw from psychological and biological literature to provide a foundation for vicarious conditioning and use memory-based methods to implement its four steps: attention, retention, reproduction, and reinforcement. Crucially, our vicarious conditioning paradigms support low-shot learning and do not require the demonstrator agent's policy nor its reward functions. We evaluate our approach in the MiniWorld Sidewalk environment, one of the few public environments that features a non-descriptive terminal condition (no reward provided upon agent death), and extend it to Box2D's CarRacing environment. Our results across both environments demonstrate that vicarious conditioning enables longer episode lengths by discouraging the agent from non-descriptive terminal conditions and guiding the agent toward desirable states. Overall, this work emulates a cognitively-plausible learning paradigm better suited to problems such as single-life learning or continual learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 52 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

20 of 52 references.

References · 20

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2014Neural Turing Machinescited by 644
  3. 2018Behavioral Cloning from Observationcited by 492
  4. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  5. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  6. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  7. 2017Third-Person Imitation Learningcited by 103
  8. 2019Recent Advances in Imitation Learning from Observationcited by 93
  9. 2022Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrationscited by 89
  10. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  11. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priorscited by 36
  12. 2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 35
8 more
  1. 2016A Siamese Long Short-Term Memory Architecture for Human Re-Identificationcited by 32
  2. 2022Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Controlcited by 28
  3. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 24
  4. 2022Hierarchical Decision Transformercited by 16
  5. 2019Interaction-aware Decision Making with Adaptive Strategies under Merging Scenarioscited by 12
  6. 2020SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Taskscited by 10
  7. 2020Reinforcement Learning with Iterative Reasoning for Merging in Dense Trafficcited by 10
  8. 2022Reinforcement learning with Demonstrations from Mismatched Task under Sparse Rewardcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Avoiding Death through Fear Intrinsic Conditioning
  2. 2026Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation
  3. 2022Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation
  4. 2023DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training
  5. 2024Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models
  6. 2024A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents
  7. 2026Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
  8. 2024Effective Reward Specification in Deep Reinforcement Learning