On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL
Nov 28, 2022
Speakers
Jinglin Chen
Speaker · 0 followers
Aditya Modi
Speaker · 0 followers
Akshay Krishnamurthy
Speaker · 5 followers
Alekh Agarwal
Speaker · 1 follower
About
We study reward-free reinforcement learning (RL) under general non-linear function approximation, and establish sample efficiency and hardness results under various standard structural assumptions. On the positive side, we propose the RFOLIVE (Reward-Free OLIVE) algorithm for sample-efficient reward-free exploration under minimal structural assumptions, which covers the previously studied settings of linear MDPs (Jin et al., 2020b), linear completeness (Zanette et al., 2020b) and low-rank MDPs with unknown representation (Modi et al., 2021). Our analyses indicate that the explorability or reachability assumptions, previously made for the latter two settings, are not necessary statistically for reward-free exploration. On the negative side, we provide a statistical hardness result for both reward-free and reward-aware exploration under linear completeness assumptions when the underlying features are unknown, showing an exponential separation between low-rank and linear completeness settings.We study reward-free reinforcement learning (RL) under general non-linear function approximation, and establish sample efficiency and hardness results under various standard structural assumptions. On the positive side, we propose the RFOLIVE (Reward-Free OLIVE) algorithm for sample-efficient reward-free exploration under minimal structural assumptions, which covers the previously studied settings of linear MDPs (Jin et al., 2020b), linear completeness (Zanette et al., 2020b) and low-rank MDPs w…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Recommender Forest for Efficient Retrieval
Watch later
Chao Feng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Lakota AI Code Camp
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Personalized Online Federated Multi-Federated Learning with Multiple Kernels
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Mutual Information Divergence: A Unified Metric for Multimodal Generative Models
Watch later
Jin-Hwa Kim, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Generating High Fidelity Synthetic Data via Coreset selection and Entropic Regularization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Federated Submodel Optimization for Hot and Cold Data Features
Watch later
Yucheng Ding, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%