Pith. sign in

REVIEW 2 cited by

Reinforcing Language Agents via Policy Optimization with Action Decomposition

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 2405.15821 v1 pith:LXZZ2N4M submitted 2024-05-23 cs.AI cs.LG

classification cs.AIcs.LG
keywords actionoptimizationagentslanguagecreditdecompositionenvironmentsintra-action
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language models as intelligent agents push the boundaries of sequential decision-making agents but struggle with limited knowledge of environmental dynamics and exponentially huge action space. Recent efforts like GLAM and TWOSOME manually constrain the action space to a restricted subset and employ reinforcement learning to align agents' knowledge with specific environments. However, they overlook fine-grained credit assignments for intra-action tokens, which is essential for efficient language agent optimization, and rely on human's prior knowledge to restrict action space. This paper proposes decomposing language agent optimization from the action level to the token level, offering finer supervision for each intra-action token and manageable optimization complexity in environments with unrestricted action spaces. Beginning with the simplification of flattening all actions, we theoretically explore the discrepancies between action-level optimization and this naive token-level optimization. We then derive the Bellman backup with Action Decomposition (BAD) to integrate credit assignments for both intra-action and inter-action tokens, effectively eliminating the discrepancies. Implementing BAD within the PPO algorithm, we introduce Policy Optimization with Action Decomposition (POAD). POAD benefits from a finer-grained credit assignment process and lower optimization complexity, leading to enhanced learning efficiency and generalization abilities in aligning language agents with interactive environments. We validate POAD across diverse testbeds, with results affirming the advantages of our approach and the correctness of our theoretical analysis.

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. BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent

    cs.CL 2026-08 conditional novelty 6.0 of 10

    A training method that blends forward answer-likelihood gains with answer-conditioned hindsight criticality to give GRPO dense per-step rewards for search agents.

  2. ProgRM: Build Better GUI Agents with Progress Rewards

    cs.AI 2025-05 conditional novelty 6.0 of 10

    ProgRM, a per-step progress reward model trained with LCS-based self-annotated labels, improves RL-trained GUI agent success rates on WikiHow relative to outcome reward models.

Pith tools