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
PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice
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.
Forward citations
Cited by 11 Pith papers
-
Pictura: Perspective-View Self-Play at Scale for Driving
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.
-
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
Equivariant RL agent synthesizes near-optimal Clifford circuits up to 30 qubits with lower two-qubit gate counts than Qiskit baselines.
-
Automatic Generation of High-Performance RL Environments
Closed-loop prompt-based translation with hierarchical verification and iterative repair produces equivalent high-performance RL environments across five cases including new TCGJax.
-
Scaling Self-Play for End-to-End Driving
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.
-
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
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.
-
Scalable Option Learning in High-Throughput Environments
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.
-
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
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...
-
Human-like autonomy emerges from self-play and a pinch of human data
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.
-
CoPark: Learning Reactive Parking via Self-Play
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.
-
A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
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.
-
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.