Pith Number

pith:IUSU7BX2

pith:2018:IUSU7BX236XGQO6S2XA3DPA465

not attested not anchored not stored refs resolved

DeepMind Control Suite

Abbas Abdolmaleki, Alistair Muldal, Andrew Lefrancq, David Budden, Diego de las Casas, Josh Merel, Martin Riedmiller, Timothy Lillicrap, Tom Erez, Yazhe Li, Yotam Doron, Yuval Tassa

The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents.

arxiv:1801.00690 v1 · 2018-01-02 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IUSU7BX236XGQO6S2XA3DPA465}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.

C2weakest assumption

That the chosen tasks and reward functions are sufficiently representative of real-world control problems and that performance on them will generalize to other domains.

C3one line summary

The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.

References

13 extracted · 13 resolved · 4 Pith anchors

[1] Layer Normalization · arXiv:1607.06450

[2] doi: 10.1109/TSMC.1983.6313077 1983 · doi:10.1109/tsmc.1983.6313077

[3] A Distributional Perspective on Reinforcement Learning · arXiv:1707.06887

[4] Simulation tools for model-based robotics: Comparison of bullet, havok, mujoco, ode and physx 2015

[5] Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control · arXiv:1708.04133

Formal links

1 machine-checked theorem link

Cited by

92 papers in Pith

A Definition and Roadmap for World Models

MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins

Fast LeWorldModel

Revisiting Action Factorization for Complex Action Spaces

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

Receipt and verification

First computed	2026-07-04T22:27:08.425426Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd

Aliases

arxiv: 1801.00690 · arxiv_version: 1801.00690v1 · doi: 10.48550/arxiv.1801.00690 · pith_short_12: IUSU7BX236XG · pith_short_16: IUSU7BX236XGQO6S · pith_short_8: IUSU7BX2

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "09ca9a5aa7251c16ad0513268c06ebd7e89db5ac2fd395f5670995b8bfb1c5ae",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2018-01-02T15:48:14Z",
    "title_canon_sha256": "11aa661c4e00a25af435dfbf79cbf609c7eb3068d3616fb0872f8cc672192052"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1801.00690",
    "kind": "arxiv",
    "version": 1
  }
}