Pith. sign in

REVIEW 4 cited by

Learning by Playing - Solving Sparse Reward Tasks from Scratch

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1802.10567 v1 pith:VIEYGTD6 submitted 2018-02-28 cs.LG cs.ROstat.ML

Martin Riedmiller , Roland Hafner , Thomas Lampe , Michael Neunert , Jonas Degrave , Tom Van de Wiele , Volodymyr Mnih , Nicolas Heess
show 1 more author
Jost Tobias Springenberg
This is my paper · ORCID
classification cs.LGcs.ROstat.ML
keywords learningauxiliaryrewardsparseagentsac-xscratchtasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Reinforcement Learning via Implicit Imitation Guidance

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A reinforcement learning method that learns a state-dependent covariance from expert-policy action differences and uses it as exploration noise, improving sample efficiency on sparse-reward continuous control tasks.

  2. Learning to Explore in Motion and Interaction Tasks

    cs.RO 2019-08 conditional novelty 6.0 of 10

    A learned generative model of past task motions, used as exploration noise in DDPG, speeds up learning of new robot manipulation and contact tasks by more than two times in simulation.

  3. Learning to combine primitive skills: A step towards versatile robotic manipulation

    cs.LG 2019-08 conditional novelty 6.0 of 10

    RLBC, a hierarchical reinforcement learning method, combines behavioral-cloned primitive skills into composite manipulation tasks using only sparse rewards and no full-task demonstrations, with sim-to-real transfer de...

  4. Solving Rubik's Cube Without Tricky Sampling

    cs.LG 2024-11 reject novelty 5.0 of 10

    The paper presents a PPO policy trained with rewards from a learned cost model, claiming 99.4% success on the 2x2x2 Rubik's Cube without search or solved-state sampling, but with weak evidential support.

Pith tools