Asynchronous Advantage Actor-Critic

Latest papers

9 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion
Oct 2, 2026Arthur Louette, Alejandro Sánchez Roncero, Gaspard Lambrechts +4Asynchronous Advantage Actor-Critic Actor-Critic Methods
University of Liège, Belgium · KTH Royal Institute of Technology, Sweden · McGill University & Mila Québec AI Institute, Canada +1
Toward Interactive Understanding of Code APIs
Sep 25, 2026Dhananjay Ashok, Jesse Thomason, Jonathan MayAsynchronous Advantage Actor-Critic AI Agent Benchmarks
Information Sciences Institute University of Southern California · University of Southern California
Privileged Critic Training Enables Sensor-Free Thruster Fault Adaptation in End-to-End RL
Aug 24, 2026Ricard Marsal I Castan, Miguel A. Olivares-MéndezAsynchronous Advantage Actor-Critic Fault-Tolerant Control
University of Luxembourg
Learning Fault-Tolerant Locomotion with Adaptive Gait Timing
Aug 7, 2026Giovanbattista Gravina, Luca Rossini, Carlo Rizzardo +2Legged Robotics Robot Locomotion
Humanoids and Human-Centered Mechatronics Research Line, Italian Institute of Technology, Genoa 16163, Italy
Adaptive Undulatory Locomotion of Snake-like Robots in Dynamic Viscous Environments via Deep Reinforcement Learning
Jul 24, 2026Tsuyoshi Kimoto, Akio Yamano, Kohei Honda +1Partially Observable RL Robotic RL
Osaka Metropolitan University, 1-1, Gakuen-cho, Naka-ku, Sakai, Osaka, Japan · Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan
WaveForward: An Omnidirectional Passive Wheeled Quadruped Robot with Casters
Jun 24, 2026Chuanlin Zhao, Qifeng Zheng, Shuhan Wang +3Robot Locomotion RL for Legged Locomotion
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Learning to replenish: A hybrid deep reinforcement learning for dynamic inventory management in the pharmaceutical supply chains
Jun 4, 2026Amandeep Kaur, Gyan PrakashInventory Control Actor-Critic Methods
Department of Management Studies ABV-Indian Institute of Information Technology and Management Gwalior-474015, Madhya Pradesh, India
Asymmetric Actor-Critic for Multi-turn LLM Agents
Mar 31, 2026Shuli Jiang, Zhaoyang Zhang, Yi Zhang +3Asynchronous Advantage Actor-Critic LLM Agent Reliability
AWS Agentic AI
GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
Mar 2, 2026Haofeng Xu, Junwei Su, Yukun Tian +3RL Stability Asynchronous Advantage Actor-Critic
School of Computing and Data Science, The University of Hong Kong · Alibaba Group · Southeast University

Oct 2, 2026J/K move · Enter open · S save

Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion

Arthur Louette, Alejandro Sánchez Roncero, Gaspard Lambrechts, Pascal Leroy+3

University of Liège, Belgium · KTH Royal Institute of Technology, Sweden · McGill University & Mila Québec AI Institute, Canada+1

Asynchronous Advantage Actor-Critic Actor-Critic Methods Partially Observable RL Visuomotor Policy Learning

Open paper AskPDF arXiv

In partially observable Markov decision processes, the optimal policy generally depends on the history of observations and past actions. Asymmetric actor-critic methods have become popular to learn such policies when additional information, such as the true state of the environment, is available during training. The critic, which is not needed at execution, is given access to the state. A critic conditioned on the state alone is generally ill-defined and yields biased policy gradients. Conditioning on the state and the history, the history-state critic restores both. In this paper, we show that conditioning the critic on the state and the policy's own memory, i.e., the internal representation of the history through which the policy selects its actions, is already well-defined and gives unbiased policy gradients, removing the need for a second recurrent approximator of the history. We call it the memory state critic. It follows that a critic based on the policy's memory need not backpropagate its loss into that memory, even though the memory is a lossy encoding of the history. We evaluate the memory-state critic in a vision-based pursuit-evasion environment between two quadrotors across two arena types. The pursuer is the learning agent, and the evader is sampled per episode from a fixed pool of heuristic behaviours. The results show that the memory-state critic outperforms the history-state critic and converges faster. In addition to being unbiased compared to the state-only critic, it maintains a slight edge in the wall arena, where the actor's history carries information that the privileged state alone does not.