Pith. sign in

REVIEW 1 cited by

Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment

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 2107.12216 v2 pith:UGJ5BVIC submitted 2021-07-26 cs.LG cs.AI

classification cs.LGcs.AI
keywords functionvaluevarianceenvironmentsstatedynamicgradienthindsight
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function becomes limited in stochastic dynamic environments, where the unexpected state dynamics and rewards will increase the variance. In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments. Particularly, to obtain an ideally unbiased gradient estimate, we propose an information-theoretic approach, which optimizes the embeddings of the future to be independent of previous actions. In our experiments, we apply the proposed hindsight value function in stochastic dynamic environments, including discrete-action environments and continuous-action environments. Compared with the standard state value function, the proposed hindsight value function consistently reduces the variance, stabilizes the training, and improves the eventual policy.

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. Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following

    cs.AI 2024-12 conditional novelty 6.0 of 10

    A few-shot LLM planner for ALFRED that relabels suboptimal trajectories with hindsight prompts reaches 25.51 SR on Test Seen, approaching or beating the full-shot HLSM baseline.

Pith tools