Braxlines: Fast And Interactive Toolkit For Rl-driven Behavior Engineering Beyond Reward Maximization

Abstract

The goal of continuous control is to synthesize desired behaviors. In reinforcement learning (RL)-driven approaches, this is often accomplished through careful task reward engineering for efficient exploration and running an off-the-shelf RL algorithm. While reward maximization is at the core of RL, reward engineering is not the only -- sometimes nor the easiest -- way for specifying complex behaviors. In this paper, we introduce \braxlines, a toolkit for fast and interactive RL-driven behavior generation beyond simple reward maximization that includes Composer, a programmatic API for generating continuous control environments, and set of stable and well-tested baselines for two families of algorithms -- mutual information maximization (MiMax) and divergence minimization (DMin) -- supporting unsupervised skill learning and distribution sketching as other modes of behavior specification. In addition, we discuss how to standardize metrics for evaluating these algorithms, which can no lon

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygu2021braxlines

Related papers

• BXRL: Behavior-explainable Reinforcement Learning (2026)0.00
• Aligning Agents Via Planning: A Benchmark For Trajectory-level Reward Modeling (2026)0.00
• Direct Behavior Specification Via Constrained Reinforcement Learning (2021)0.00
• Rlexplore: Accelerating Research In Intrinsically-motivated Reinforcement Learning (2024)5.33
• Designing Rewards For Fast Learning (2022)0.00
• Rltools: A Fast, Portable Deep Reinforcement Learning Library For Continuous Control (2023)0.00
• Test-driven Reinforcement Learning In Continuous Control (2025)0.00
• Scilab-rl: A Software Framework For Efficient Reinforcement Learning And Cognitive Modeling Research (2024)0.00