Caption
Figure 2: Discounted return (J), Cumulative return (R), Value function on the initial state (V), and policy entropy on the PyBullet HopeprBulletEnv-v0 Task
Tateo_Davide_Deep Reinforcement Learning_Benchmarking algorithms and applications_Figure2
Tateo_Davide_Deep Reinforcement Learning_Benchmarking algorithms and applications_Figure2
