Pith. sign in

REVIEW 11 cited by

PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice

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 2406.12905 v1 pith:K7JDIDIE submitted 2024-06-11 cs.LG cs.AIcs.MA

PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice

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

You have an environment, a model, and a reinforcement learning library that are designed to work together but don't. PufferLib makes them play nice. The library provides one-line environment wrappers that eliminate common compatibility problems and fast vectorization to accelerate training. With PufferLib, you can use familiar libraries like CleanRL and SB3 to scale from classic benchmarks like Atari and Procgen to complex simulators like NetHack and Neural MMO. We release pip packages and prebuilt images with dependencies for dozens of environments. All of our code is free and open-source software under the MIT license, complete with baselines, documentation, and support at pufferai.github.io.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Pictura: Perspective-View Self-Play at Scale for Driving

    cs.CV 2026-07 conditional novelty 7.0

    Perspective-image self-play at 50B agent steps produces a driving policy that approaches privileged-vector performance in-domain and transfers better to re-rendered Waymo layouts.

  2. Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis

    quant-ph 2026-05 unverdicted novelty 7.0

    Equivariant RL agent synthesizes near-optimal Clifford circuits up to 30 qubits with lower two-qubit gate counts than Qiskit baselines.

  3. Automatic Generation of High-Performance RL Environments

    cs.LG 2026-03 conditional novelty 7.0

    Closed-loop prompt-based translation with hierarchical verification and iterative repair produces equivalent high-performance RL environments across five cases including new TCGJax.

  4. Scaling Self-Play for End-to-End Driving

    cs.RO 2026-06 unverdicted novelty 6.0

    Self-play DAgger training in a batched pixel renderer produces end-to-end driving policies that reach competitive performance on HUGSIM and NAVSIM-v2 after real-world adaptation and improve with more self-play compute.

  5. TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

    cs.CV 2026-06 conditional novelty 6.0

    Self-play in a vector simulator trains a driving teacher; a vision student aligned by action and low-rank structural losses drives end-to-end without expert trajectory supervision.

  6. Scalable Option Learning in High-Throughput Environments

    cs.LG 2025-08 unverdicted novelty 6.0

    SOL is a new hierarchical RL algorithm that reaches 35x higher throughput and outperforms flat agents when trained on 30 billion frames in NetHack while showing positive scaling.

  7. TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

    cs.CV 2026-06 unverdicted novelty 5.0

    TerraTransfer decouples self-play policy pretraining from vision alignment via KL divergence and low-rank loss to produce end-to-end driving policies without expert demonstrations, matching prior methods on closed-loo...

  8. Human-like autonomy emerges from self-play and a pinch of human data

    cs.LG 2026-06 unverdicted novelty 5.0

    Self-play RL regularized with 30 minutes of human data produces driving policies that coordinate with humans, training in 15 hours on one GPU with 2500x less data than imitation learning.

  9. CoPark: Learning Reactive Parking via Self-Play

    cs.RO 2026-06 unverdicted novelty 5.0

    CoPark uses multi-agent self-play RL with a residual policy and threat-modulated asymmetric prior release to achieve 70-85% success and 3-6% collision rates in reactive parking benchmarks.

  10. A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations

    cs.MA 2026-04 unverdicted novelty 5.0

    A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.

  11. Gymnasium: A Standard Interface for Reinforcement Learning Environments

    cs.LG 2024-07 accept novelty 5.0

    Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.