mlsanityData to 14 Oct 2026

Multi-action Tangled Program Graphs for Multi-task Reinforcement Learning with Continuous Control

arXiv 2604.25369 ↗First posted 28 Apr 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for specific tasks. To further challenge algorithms, Multi-Task RL (MTRL) environments have been introduced, requiring a single model to learn multiple behaviors. The Tangled Program Graph (TPG) algorithm is a Genetic Programming (GP) algorithm designed for discrete MTRL environments. Recently, the MAPLE algorithm has been proposed, as another GP algorithm that achieves high results in single task continuous RL environments. A variation of the TPG is proposed alongside MAPLE, named Multi-Action TPG (MATPG) that aggregates MAPLE agents, and creates a control flow to activate them. Initially tested on single task RL environments only, MATPG achieved similar results to MAPLE. In this work, we present a new benchmark based on the MuJoCo Half Cheetah from Gymnasium. This benchmark features five distinct obstacles that are randomly positioned in front of the agent, each of which demands a unique behavior. This benchmark serves as a use case for MATPG, to prove its ability as a GP solution for continuous MTRL environments. Our experiments demonstrate its superiority in this multi-task use case when combined with lexicase selection. Furthermore, we examine the interpretability of the evolved graph, revealing that the decision flow of the model is fully interpretable.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 33 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

10 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Position: Lifetime tuning is incompatible with continual reinforcement learning2 Apr

Other references · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  5. 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 143
  6. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 46
  7. 2020Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Controlcited by 28
  8. 2019A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithmscited by 27
  9. 2017Benchmark Environments for Multitask Learning in Continuous Domainscited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
  2. 2025Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
  3. 2024Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs
  4. 2024Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
  5. 2025Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
  6. 2024Scaling Team Coordination on Graphs with Reinforcement Learning
  7. 2024Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
  8. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning