ResearchBenchmarksReinforcement Learning on Reacher (IQM of returns)Reinforcement Learning on Reacher (IQM of returns)Follow-11.69IQM ReturnsA2ER-35.7868-29.5309-23.275-17.0191Apr 29, 2025Evaluation resultsMethodMethodLinksIQM ReturnsA2ERblock strategy=trueblock strategy=true2025.04-11.69FIFO2025.04-12.29A2ER-Bblock strategy=falseblock strategy=false2025.04-16.08DERalpha=1alpha=12025.04-34.86