Pith. sign in

REVIEW 13 cited by

Open-Ended Learning Leads to Generally Capable Agents

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 2107.12808 v2 pith:223MK4VH submitted 2021-07-27 cs.LG cs.AIcs.MA

Open-Ended Learning Leads to Generally Capable Agents

classification cs.LG cs.AIcs.MA
keywords agentagentslearningbehaviourtasksspacebehavioursbeyond
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and demonstrate the ability to train agents that are generally capable across this vast space and beyond. The environment is natively multi-agent, spanning the continuum of competitive, cooperative, and independent games, which are situated within procedurally generated physical 3D worlds. The resulting space is exceptionally diverse in terms of the challenges posed to agents, and as such, even measuring the learning progress of an agent is an open research problem. We propose an iterative notion of improvement between successive generations of agents, rather than seeking to maximise a singular objective, allowing us to quantify progress despite tasks being incomparable in terms of achievable rewards. We show that through constructing an open-ended learning process, which dynamically changes the training task distributions and training objectives such that the agent never stops learning, we achieve consistent learning of new behaviours. The resulting agent is able to score reward in every one of our humanly solvable evaluation levels, with behaviour generalising to many held-out points in the universe of tasks. Examples of this zero-shot generalisation include good performance on Hide and Seek, Capture the Flag, and Tag. Through analysis and hand-authored probe tasks we characterise the behaviour of our agent, and find interesting emergent heuristic behaviours such as trial-and-error experimentation, simple tool use, option switching, and cooperation. Finally, we demonstrate that the general capabilities of this agent could unlock larger scale transfer of behaviour through cheap finetuning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

    cs.AI 2023-06 conditional novelty 8.0

    LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.

  3. Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines

    cs.LG 2025-07 unverdicted novelty 7.0

    Multitask Preplay replays experience from pursued tasks as starting points for counterfactual simulation of unpursued tasks to learn predictive representations that support fast generalization in humans and machines.

  4. Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

    cs.LG 2026-07 conditional novelty 6.0

    Closed-loop agentic probing plus minimality/sufficiency masking recovers compact task-sufficient world-model latents that improve sample-efficient policy learning and cross-task generalization.

  5. Hierarchical Experimentalist Agents

    cs.AI 2026-06 unverdicted novelty 6.0

    HExA is a training-free agent framework that improves LLM performance on novel physics tasks from 2% to 77% by iteratively designing experiments and composing learned skills.

  6. Task diversity produces systematic transfer but inhibits continual reinforcement learning

    cs.LG 2026-05 unverdicted novelty 6.0

    Task diversity along map, object, and hierarchy axes produces local transfer across shifts in a new continual RL benchmark but fails to sustain learning as the number of shifts grows.

  7. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

    cs.AI 2024-08 conditional novelty 6.0

    Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.

  8. Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

    cs.AI 2023-05 conditional novelty 6.0

    GITM uses LLMs to generate action plans from text knowledge and memory, enabling agents to complete long-horizon Minecraft tasks at much higher success rates than prior RL methods.

  9. Robots Need More than VLA and World Models

    cs.RO 2026-06 unverdicted novelty 5.0

    The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.

  10. Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments

    cs.LG 2026-03 conditional novelty 5.0

    PPO plateaus can be avoided by increasing the number of parallel environments, which reduces both the outer-loop step size and update noise; scaling to 1M environments sustained improvement to 1T transitions.

  11. Agentic Services Computing

    cs.SE 2025-09 conditional novelty 5.0

    A position and survey paper that defines Agentic Services Computing, a lifecycle-based framework for engineering LLM agents as governed, first-class services.

  12. A Compositional Framework for Open-ended Intelligence

    cs.LG 2026-06 unverdicted novelty 4.0

    Open-ended intelligence is formalized as the compositional closure L(P,C) of primitives P under operators C, with next primitive prediction proposed as an objective to acquire reusable primitives and grammar for lifel...

  13. Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent

    cs.AI 2026-02 unverdicted novelty 2.0

    A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.