Attraction-repulsion Actor-critic For Continuous Control Reinforcement Learning

Abstract

Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive operations between current members of the population and previously observed policies. Empirical results on the MuJoCo suite demonstrate a high performance gain for our algorithm compared to prior work, including Soft-Actor Critic (SAC).

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydoan2019attraction

Related papers

• Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76
• Deep RL With Information Constrained Policies: Generalization In Continuous Control (2020)0.00
• Improving Exploration In Soft-actor-critic With Normalizing Flows Policies (2019)0.00
• Solving Continuous Control Via Q-learning (2022)0.00
• Discrete And Continuous Action Representation For Practical RL In Video Games (2019)0.00
• Policy Optimization In A Noisy Neighborhood: On Return Landscapes In Continuous Control (2023)0.00
• Broad Critic Deep Actor Reinforcement Learning For Continuous Control (2024)0.00
• Context-based Soft Actor Critic For Environments With Non-stationary Dynamics (2021)0.00