arXiv Machine Learning
Asymmetric On-Policy Distillation Learns In-Context Exploration
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 5
EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation
EVOL is a framework that uses a knowledge‑tracing simulator to generate per‑learner expert demonstrations via evolutionary search, and then trains a deployment‑free policy that distills these demonstrations into a feed‑forward learner. The method employs an asymmetric actor‑critic architecture, where the actor plans blindly as in real deployment while the critic has access to privileged simulator state during training. Across three educational datasets and varying path lengths, EVOL outperforms eight baselines and shows that the quality of evolutionary experts, rather than the imitation objective, drives final performance.
arXiv Machine Learning
Jun 2
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
arXiv AI
Aug 3
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
arXiv:2607. 29617v1 Announce Type: cross Abstract: Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model training.
arXiv AI
Jun 2
ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
arXiv:2603. 15956v3 Announce Type: replace-cross Abstract: Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data.
arXiv AI
Aug 13
TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
arXiv:2605. 12236v2 Announce Type: replace-cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.
arXiv Machine Learning
Aug 13
Adaptation of Generalist Robot Policies with Minimal Data
arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.