Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning
cs.LG, cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Poke and Strike: Learning Task-Informed Exploration Policies
- Model-based Adversarial Imitation Learning
- Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
- DITTO: Offline Imitation Learning with World Models
- Challenges of Real-World Reinforcement Learning
- Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- Temporal Difference Learning for Model Predictive Control
- Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
- Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias
- Hybrid Inverse Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks