mlsanityData to 14 Oct 2026

Velocity-History-Based Soft Actor-Critic Tackling IROS'24 Competition "AI Olympics with RealAIGym"

arXiv 2410.20096 ↗First posted 26 Oct 2024cs.ROcited by 1

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

The ``AI Olympics with RealAIGym'' competition challenges participants to stabilize chaotic underactuated dynamical systems with advanced control algorithms. In this paper, we present a novel solution submitted to IROS'24 competition, which builds upon Soft Actor-Critic (SAC), a popular model-free entropy-regularized Reinforcement Learning (RL) algorithm. We add a `context' vector to the state, which encodes the immediate history via a Convolutional Neural Network (CNN) to counteract the unmodeled effects on the real system. Our method achieves high performance scores and competitive robustness scores on both tracks of the competition: Pendubot and Acrobot.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 14 references that are in the map. First posted on arXiv 26 Oct 2024.

Builds on

5 of 14 references.

References · 5

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  4. 2019Assessing Transferability from Simulation to Reality for Reinforcement Learningcited by 33
  5. 2023Solving the swing-up and balance task for the Acrobot and Pendubot with SACcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Effective Reinforcement Learning Control using Conservative Soft Actor-Critic
  2. 2024AI Olympics challenge with Evolutionary Soft Actor Critic
  3. 2025Unlocking the Potential of Soft Actor-Critic for Imitation Learning
  4. 2024Generalizing soft actor-critic algorithms to discrete action spaces
  5. 2025Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition
  6. 2024Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients
  7. 2025Finetuning Deep Reinforcement Learning Policies with Evolutionary Strategies for Control of Underactuated Robots
  8. 2026Off-Policy Actor-Critic with Sigmoid-Bounded Entropy for Real-World Robot Learning