ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs

Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy

Abstract: In recent years, reinforcement learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent’s behavior. Existing al...