Pith. sign in

REVIEW 2 cited by

Continual Reinforcement Learning with Multi-Timescale Replay

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 2004.07530 v1 pith:SGSA52MP submitted 2020-04-16 cs.LG cs.AIstat.ML

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

In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent. The basic MTR buffer comprises a cascade of sub-buffers that accumulate experiences at different timescales, enabling the agent to improve the trade-off between adaptation to new data and retention of old knowledge. We also combine the MTR framework with invariant risk minimization, with the idea of encouraging the agent to learn a policy that is robust across the various environments it encounters over time. The MTR methods are evaluated in three different continual learning settings on two continuous control tasks and, in many cases, show improvement over the baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Uncertainty Prioritized Experience Replay

    cs.LG 2025-06 conditional novelty 6.0 of 10

    UPER uses ensemble-based epistemic and aleatoric uncertainty to compute an information gain priority for experience replay, outperforming TD-error prioritization on Atari-57.

  2. Continual Reinforcement Learning for Digital Twin Synchronization Optimization

    cs.NI 2025-01 conditional novelty 5.0 of 10

    A continual reinforcement learning scheduler with multi-timescale replay and a resource-constrained actor-critic reduces digital twin state estimation error by up to 55.2% in simulation.

Pith tools