The paper gives the first provable polynomial-sample and quasi-polynomial-time guarantees for expert distillation and belief-weighted asymmetric actor-critic in POMDPs with privileged state information.
Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Supervised learning is often computationally easy in practice. But to what extent does this mean that other modes of learning, such as reinforcement learning (RL), ought to be computationally easy by extension? In this work we show the first cryptographic separation between RL and supervised learning, by exhibiting a class of block MDPs and associated decoding functions where reward-free exploration is provably computationally harder than the associated regression problem. We also show that there is no computationally efficient algorithm for reward-directed RL in block MDPs, even when given access to an oracle for this regression problem. It is known that being able to perform regression in block MDPs is necessary for finding a good policy; our results suggest that it is not sufficient. Our separation lower bound uses a new robustness property of the Learning Parities with Noise (LPN) hardness assumption, which is crucial in handling the dependent nature of RL data. We argue that separations and oracle lower bounds, such as ours, are a more meaningful way to prove hardness of learning because the constructions better reflect the practical reality that supervised learning by itself is often not the computational bottleneck.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provable Partially Observable Reinforcement Learning with Privileged Information
The paper gives the first provable polynomial-sample and quasi-polynomial-time guarantees for expert distillation and belief-weighted asymmetric actor-critic in POMDPs with privileged state information.