SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.02276 · NeurIPS · 2024

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs

Jeff Clune, Ben Norman

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 2 no recorded run), measured 2026-11-22; 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/2307.02276.json · badge: /api/ran/2307.02276.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
btnorman/First-Explore canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
tokenize Ran
ran; our contract draft was wrong, not the code
btnorman/First-Explore/tiny_world/tiny_world_first_explore.py
code served (permissive licence) · get_code("6deaee162fc9967d")
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 tuple. 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 jax
import jax.numpy as jnp
import numpy as np

ACT_DIM = 3

# Create small test batches
# actions_batch needs to be shape (batch, seq_len) with integer indices in [0, ACT_DIM)
# The function applies vmap twice, so we need a 2D array
actions_batch = jnp.array([[0, 1, 2, 0],
                           [1, 2, 0, 1]], dtype=jnp.int32)

# rewards_batch needs to be shape (batch, seq_len) 
# After expand_dims(rewards_batch, 2), it becomes (batch, seq_len, 1)
rewards_batch = jnp.array([[0.5, 1.0, -0.5, 0.2],
                           [0.3, -0.1, 0.8, 0.4]], dtype=jnp.float32)

ARGS = {
    "actions_batch": actions_batch,
    "rewards_batch": rewards_batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
LTE Not yet run
unverified (harvested, no recorded run)
btnorman/First-Explore/lte_code/lte_model5.py
code served (permissive licence) · get_code("e6f9ae92ebaa1065")
How it ran

no invocation recorded.

modFlaxGPT2Module Not yet run
unverified (harvested, no recorded run)
btnorman/First-Explore/lte_code/lte_model5.py
code served (permissive licence) · get_code("1eb21499b3456369")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Standard reinforcement learning (RL) agents never intelligently explore like a human (i.e. taking into account complex domain priors and adapting quickly based on previous exploration). Across episodes, RL agents struggle to perform even simple exploration strategies, for example systematic search that avoids exploring the same location multiple times. This poor exploration limits performance on challenging domains. Meta-RL is a potential solution, as unlike standard RL, meta-RL can learn to explore, and potentially learn highly complex strategies far beyond those of standard RL, strategies such as experimenting in early episodes to learn new skills, or conducting experiments to learn about the current environment. Traditional meta-RL focuses on the problem of learning to optimally balance exploration and exploitation to maximize the cumulative reward of the episode sequence (e.g., aiming to maximize the total wins in a tournament -while also improving as a player). We identify a new challenge with state-of-the-art cumulative-reward meta-RL methods. When optimal behavior requires exploration that sacrifices immediate reward to enable higher subsequent reward, existing state-of-the-art cumulative-reward meta-RL methods become stuck on the local optimum of failing to explore. Our method, First-Explore, overcomes this limitation by learning two policies: one to solely explore, and one to solely exploit. When exploring requires forgoing early-episode reward, First-Explore significantly outperforms existing cumulative meta-RL methods. By identifying and solving the previously unrecognized problem of forgoing reward in early episodes, First-Explore represents a significant step towards developing meta-RL algorithms capable of human-like exploration on a broader range of domains.

For agents

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

get_harvested_code_for_paper("2307.02276")
get_code_for_paper("2307.02276")
have("2307.02276")

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

curl https://syntology.ai/api/ran/2307.02276.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.02276.svg)](https://syntology.ai/paper/2307.02276)

Connect an agent — have() is free.