Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, And Decision Concepts

Abstract

Learning a control policy capable of adapting to time-varying and potentially evolving system dynamics has been a great challenge to the mainstream reinforcement learning (RL). Mainly, the ever-changing system properties would continuously affect how the RL agent interacts with the state space through its actions, which effectively (re-)introduces concept drifts to the underlying policy learning process. We postulated that higher adaptability for the control policy can be achieved by characterizing and representing actions with extra "degrees of freedom" and thereby, with greater flexibility, adjusts to variations from the action's "behavioral" outcomes, including how these actions get carried out in real time and the shift in the action set itself. This paper proposes a Bayesian-flavored generalized RL framework by first establishing the notion of parametric action model to better cope with uncertainty and fluid action behaviors, followed by introducing the notion of reinforcement fie

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychiu2022generalized

Related papers

• Demystifying Reinforcement Learning In Time-varying Systems (2022)0.00
• Unified Algorithms For RL With Decision-estimation Coefficients: PAC, Reward-free, Preference-based Learning, And Beyond (2022)5.24
• Live In The Moment: Learning Dynamics Model Adapted To Evolving Policy (2022)0.00
• Dynamic Reinforcement Learning For Actors (2025)0.00
• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• A General Markov Decision Process Framework For Directly Learning Optimal Control Policies (2019)0.00
• Addressing Action Oscillations Through Learning Policy Inertia (2021)7.81
• Reinforcement Learning With Experience Replay And Adaptation Of Action Dispersion (2022)0.00