Pith. sign in

REVIEW 4 cited by

Learning Reward for Robot Skills Using Large Language Models via Self-Alignment

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 2405.07162 v3 pith:JE7TCFSF submitted 2024-05-12 cs.RO cs.AI

classification cs.ROcs.AI
keywords rewardfunctionslearningmethodlanguagelargemodelsprocess
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However, the proposed reward function can be imprecise, thus ineffective which requires to be further grounded with environment information. We proposed a method to learn rewards more efficiently in the absence of humans. Our approach consists of two components: We first use the LLM to propose features and parameterization of the reward, then update the parameters through an iterative self-alignment process. In particular, the process minimizes the ranking inconsistency between the LLM and the learnt reward functions based on the execution feedback. The method was validated on 9 tasks across 2 simulation environments. It demonstrates a consistent improvement over training efficacy and efficiency, meanwhile consuming significantly fewer GPT tokens compared to the alternative mutation-based method.

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. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  2. Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning

    cs.RO 2025-09 conditional novelty 5.0 of 10

    RE-GoT combines graph-of-thoughts planning in LLMs with VLM feedback from rollout videos to automatically write and refine RL reward functions, beating prior LLM-based reward design on RoboGen and ManiSkill2.

  3. Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding

    cs.RO 2025-07 conditional novelty 5.0 of 10

    AdaRPG uses GPT-4o, GroundingDINO, and SAM to locate and segment the movable part, a part-affordance model to choose a grasp, and GPT-4o to write the control loop, outperforming prior methods on new articulated objects.

  4. Multi-agent Embodied AI: Advances and Future Directions

    cs.AI 2025-05 conditional novelty 3.0 of 10

    A survey that maps multi-agent embodied AI methods and benchmarks across control, learning, and generative-model categories, and lists open challenges.

Pith tools