Ego-foresight: Self-supervised Learning Of Agent-aware Representations For Improved RL

Abstract

Despite the significant advances in Deep Reinforcement Learning (RL) observed in the last decade, the amount of training experience necessary to learn effective policies remains one of the primary concerns in both simulated and real environments. Looking to solve this issue, previous work has shown that improved efficiency can be achieved by separately modeling the agent and environment, but usually requires a supervisory signal. In contrast to RL, humans can perfect a new skill from a small number of trials and often do so without a supervisory signal, making neuroscientific studies of human development a valuable source of inspiration for RL. In particular, we explore the idea of motor prediction, which states that humans develop an internal model of themselves and of the consequences that their motor commands have on the immediate sensory inputs. Our insight is that the movementofthe agent provides a cue that allows the duality between the agent and environment to be learned. To ins

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynunes2024ego

Related papers

• Data-efficient Reinforcement Learning With Self-predictive Representations (2020)0.00
• Learning Latent Representations To Influence Multi-agent Interaction (2020)0.00
• An Empirical Study On The Power Of Future Prediction In Partially Observable Environments (2024)0.00
• Improving Generalization To New Environments And Removing Catastrophic Forgetting In Reinforcement Learning By Using An Eco-system Of Agents (2022)0.00
• Decomposing The Prediction Problem; Autonomous Navigation By Neorl Agents (2021)0.00
• From Centralized To Self-supervised: Pursuing Realistic Multi-agent Reinforcement Learning (2023)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00
• Accelerating Reinforcement Learning Agent With Eeg-based Implicit Human Feedback (2020)0.00