Pith Number

pith:PIQSC3RZ

pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX

not attested not anchored not stored refs resolved

Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning

Dominik \.Zurek, Kamil Faber, Marcin Pietro\'n, Pawe{\l} Gajewski

A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.

arxiv:2410.06347 v2 · 2024-10-08 · cs.RO · 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{PIQSC3RZPOCTKT4WBQXOQJENTX}

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

Experimental results demonstrate that our approach outperforms state-of-the-art online baselines in complex tasks and maintains robustness in sparse-reward settings, even with limited expert demonstrations.

C2weakest assumption

The newly released offline dataset for the Franka Emika Panda platform contains sufficient coverage of varying goals and task distributions to support generalization of the goal-conditioned policy.

C3one line summary

A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.

References

47 extracted · 47 resolved · 4 Pith anchors

[1] Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning 2023

[2] Efficient reinforcement learning for autonomous driving with parameterized skills and priors 2023

[3] Accelerating reinforcement learning for autonomous driving using task-agnostic and ego-centric motion skills 2022

[4] A review paper on implementing reinforcement learning technique in optimising games performance 2019

[5] Modeling decisions in games using reinforcement learning 2017

Cited by

5 papers in Pith

MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners

Focal Plate Prototyping for Modular Focal Planes of Stage-5 Instruments For Ground-Based Telescopes

Thermal Characterization of a 6-Positioner, 6.2-mm-Pitch Module for Stage-5 Telescopes

MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners

Receipt and verification

First computed	2026-06-30T01:17:20.696364Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e

Aliases

arxiv: 2410.06347 · arxiv_version: 2410.06347v2 · doi: 10.48550/arxiv.2410.06347 · pith_short_12: PIQSC3RZPOCT · pith_short_16: PIQSC3RZPOCTKT4W · pith_short_8: PIQSC3RZ

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/PIQSC3RZPOCTKT4WBQXOQJENTX \
  | 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: 7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "357b46dd5d9fff5059260461cb086f17d457ee040860ae14470c708be443c5b9",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2024-10-08T20:35:30Z",
    "title_canon_sha256": "c8fe069eba42c134b57383c0da4518828a371a88f8c5e640b133ad5a7366ae57"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.06347",
    "kind": "arxiv",
    "version": 2
  }
}