Bildunterschrift
Figure 1: Discounted return (J), Cumulative return (R), Value function on the initial state (V), and policy entropy on the MuJoCo Hopper-v3 Task
Tateo_Davide_Deep Reinforcement Learning_Benchmarking algorithms and applications_Figure1
Tateo_Davide_Deep Reinforcement Learning_Benchmarking algorithms and applications_Figure1
