Pith. sign in

REVIEW 5 cited by

Hyperparameter Selection for Offline Reinforcement Learning

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 2007.09055 v1 pith:RAIUAFB4 submitted 2020-07-17 cs.LG cs.AIstat.ML

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

Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by evaluating policies corresponding to each hyperparameter setting in the environment. This online execution is often infeasible and hence undermines the main aim of offline RL. Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i.e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data. Through large-scale empirical evaluation we show that: 1) offline RL algorithms are not robust to hyperparameter choices, 2) factors such as the offline RL algorithm and method for estimating Q values can have a big impact on hyperparameter selection, and 3) when we control those factors carefully, we can reliably rank policies across hyperparameter choices, and therefore choose policies which are close to the best policy in the set. Overall, our results present an optimistic view that offline hyperparameter selection is within reach, even in challenging tasks with pixel observations, high dimensional action spaces, and long horizon.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Active Offline-to-Online Reinforcement Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    UCB selection driven by local linear forecasts of fine-tuning returns allocates limited online interactions more effectively than single-policy or equal-budget O2O-RL baselines across continuous-control tasks.

  2. Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations

    cs.LG 2026-07 conditional novelty 6.0 of 10

    RLVR training teaches a 30B LLM to strategically explore a multi-buyer market and extract 70% of available surplus, outperforming frontier models up to 1T parameters in concurrent negotiation.

  3. Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    ADWM learns a latent diffusion world model with per-transition independent denoising and policy-conditioned guidance to enable accurate offline evaluation of LLM agent policies.

  4. Accelerating Detailed Routing Convergence through Offline Reinforcement Learning

    cs.AR 2025-12 conditional novelty 6.0 of 10

    A conservative Q-learning model that selects per-iteration routing cost weights speeds up OpenROAD detailed routing on ISPD19 benchmarks by 1.56x on average without worsening DRVs.

  5. Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction

    cs.RO 2025-07 conditional novelty 5.0 of 10

    A neural behavior classifier trained on teleoperated joint trajectories is proposed and tested as an offline meta-evaluator for imitation learning policies in human-robot interaction.

Pith tools