Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

HarmonyDream: Task Harmonization Inside World Models

ICML 24 2024 51.6 method

TLDR

HarmonyDream balances observation and reward modeling in world models for sample-efficient MBRL, achieving state-of-the-art on Atari 100K.

Reasoning

The paper provides a clear empirical investigation and insight into task imbalance in world models, proposing a simple yet effective dynamic loss adjustment method. Strengths include strong experimental results on visual robotic tasks and Atari benchmarks, but the approach is limited to simulated environments and may not generalize to real-world settings.

Read-first score

Read-first score 51.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 43.

Reproducibility 18%
81

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code,github

Recency 6%
75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Methodology quality 18%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,experiment,result

Topical relevance 29%
61.4

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Citation impact 18%
10.1

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=1

Citation velocity 12%
5.9

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.33

Field roles

Methodology anchorReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 675.

Keyword Scores

world model
10
model-based reinforcement learning world model
10
world dynamics prediction
7
generative world model
6
world simulator
5
video world model
3
interactive world model
2

Deep Analysis

Innovations

  • Uncovering the overlooked potential of sample-efficient MBRL by mitigating the domination of either observation or reward modeling in world models
  • Proposing HarmonyDream, a method that automatically adjusts loss coefficients to maintain a dynamic equilibrium between observation and reward modeling tasks
  • Achieving new state-of-the-art results on the Atari 100K benchmark with 10%-69% absolute performance boosts on visual robotic tasks

Methodology

The authors conduct a dedicated empirical investigation to understand the roles of observation and reward modeling in world models. Based on insights that observation modeling struggles with environment complexity and limited capacity, while reward modeling lacks rich learning signals, they propose HarmonyDream, which automatically adjusts loss coefficients to maintain task harmonization. The method is evaluated on visual robotic tasks and the Atari 100K benchmark using a base MBRL method.

Key Results

HarmonyDream yields 10%-69% absolute performance improvements on visual robotic tasks and sets a new state-of-the-art result on the Atari 100K benchmark.

Tags