Pith. sign in

REVIEW 2 cited by

Real-time Policy Distillation in Deep 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 1912.12630 v1 pith:F2WRGIUL submitted 2019-12-29 cs.LG cs.AIstat.ML

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

Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is underexplored in deep reinforcement learning, and existing approaches are computationally inefficient, resulting in a long distillation time. In addition, the effectiveness of the distillation process is still limited to the model capacity. We propose a new distillation mechanism, called real-time policy distillation, in which training the teacher model and distilling the policy to the student model occur simultaneously. Accordingly, the teacher's latest policy is transferred to the student model in real time. This reduces the distillation time to half the original time or even less and also makes it possible for extremely small student models to learn skills at the expert level. We evaluated the proposed algorithm in the Atari 2600 domain. The results show that our approach can achieve full distillation in most games, even with compression ratios up to 1.7%.

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. Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning

    cs.MA 2025-02 conditional novelty 6.0 of 10

    Per-agent low-rank adapters on a shared backbone let multi-agent policies specialize at a fraction of the memory cost of separate networks, with competitive benchmark performance.

  2. Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation

    cs.LG 2024-11 conditional novelty 5.0 of 10

    Task-Agnostic Policy Distillation pretrains a continual RL agent with curiosity-driven exploration and policy distillation, yielding faster learning and higher scores on five Atari games.

Pith tools