Pith. sign in

REVIEW 1 cited by

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.12484 v2 pith:2PEDOMA4 submitted 2020-06-22 cs.LG cs.AImath.OCstat.ML

classification cs.LGcs.AImath.OCstat.ML
keywords learningpomdpsnumberreinforcementalgorithmchallengeefficientexploration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Partial observability is a common challenge in many reinforcement learning applications, which requires an agent to maintain memory, infer latent states, and integrate this past information into exploration. This challenge leads to a number of computational and statistical hardness results for learning general Partially Observable Markov Decision Processes (POMDPs). This work shows that these hardness barriers do not preclude efficient reinforcement learning for rich and interesting subclasses of POMDPs. In particular, we present a sample-efficient algorithm, OOM-UCB, for episodic finite undercomplete POMDPs, where the number of observations is larger than the number of latent states and where exploration is essential for learning, thus distinguishing our results from prior works. OOM-UCB achieves an optimal sample complexity of $\tilde{\mathcal{O}}(1/\varepsilon^2)$ for finding an $\varepsilon$-optimal policy, along with being polynomial in all other relevant quantities. As an interesting special case, we also provide a computationally and statistically efficient algorithm for POMDPs with deterministic state transitions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LLM-Guided Probabilistic Program Induction for POMDP Model Estimation

    cs.AI 2025-05 conditional novelty 6.0 of 10

    LLM-guided probabilistic program induction can learn low-complexity POMDP models from ten demonstrations and outperform tabular learning, behavior cloning, and direct LLM planning in simulated and real robot domains.

Pith tools