Deep Ensemble Reinforcement Learning with Multiple Deep Deterministic Policy Gradient Algorithm

Table 4

Performance comparison of the aggregated policy and subpolicies.

Policy	Steps	Total reward (points)	Complete one lap
Subpolicy1	246	16690.60	No
Subpolicy2	246	15413.12	No
Subpolicy3	102	−1252.46	No
Aggregated policy	457	31603.37	Yes