SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.09031 · ICLR · 2022

Hindsight Foresight Relabeling for Meta-Reinforcement Learning

Tanmay Gangwani, Jian Peng, Michael Wan

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2109.09031.json · badge: /api/ran/2109.09031.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
michaelwan11/hfr canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
deep_update_dict Ran
ran; our contract draft was wrong, not the code
michaelwan11/hfr/launch_experiment.py
code served (permissive licence) · get_code("e937b70b07bfc9d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - deep_update_dict(fr, to) takes two parameters
# - It iterates over items in 'fr' dict
# - For each value, if it's a dict, recursively calls deep_update_dict(v, to[k])
# - Otherwise, updates to[k] = v
# - Returns the updated 'to' dict

# Construct test arguments:
# 'fr' should be a dict with nested dicts and scalar values
# 'to' should be a dict with matching structure to be updated

fr = {
    "model": {
        "learning_rate": 0.001,
        "batch_size": 32,
        "layers": {
            "hidden_dim": 128,
            "dropout": 0.5
        }
    },
    "training": {
        "epochs": 10,
        "optimizer": "adam"
    },
    "seed": 42
}

to = {
    "model": {
        "learning_rate": 0.01,
        "batch_size": 16,
        "layers": {
            "hidden_dim": 64,
            "dropout": 0.3
        }
    },
    "training": {
        "epochs": 5,
        "optimizer": "sgd"
    },
    "seed": 0
}

ARGS = {
    "fr": fr,
    "to": to
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
deep_update_dict 13 other papers
5 dated earlier, 8 later
1903.08254 (2019-03)
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
2006.08170 (2020-06)
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
2009.13891 (2020-09)
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
and 10 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at test time after experiencing only a few trajectories, the meta-training process is still sample-inefficient. Prior works have found that in the multi-task RL setting, relabeling past transitions and thus sharing experience among tasks can improve sample efficiency and asymptotic performance. We apply this idea to the meta-RL setting and devise a new relabeling method called Hindsight Foresight Relabeling (HFR). We construct a relabeling distribution using the combination of hindsight, which is used to relabel trajectories using reward functions from the training task distribution, and foresight, which takes the relabeled trajectories and computes the utility of each trajectory for each task. HFR is easy to implement and readily compatible with existing meta-RL algorithms. We find that HFR improves performance when compared to other relabeling methods on a variety of meta-RL tasks 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.09031")
get_code_for_paper("2109.09031")
have("2109.09031")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.09031.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.09031.svg)](https://syntology.ai/paper/2109.09031)

Connect an agent — have() is free.