| evaluation/total.timesteps,evaluation/episode.final_reward,evaluation/episode.return,evaluation/episode.length,evaluation/episode.duration,evaluation/episode.normalized_return,step |
| 1209.15,1.150696055266459,121.53413858285019,116.9,0.12336223125457764,4.357145280348907,1 |
| 9124.7,4.0203709834617065,2180.7230131955757,653.9,0.5762263298034668,67.62778982707455,100000 |
| 20497.9,4.381063851558535,1597.9353253084396,485.5,0.441238260269165,49.72105329546334,200000 |
| 29372.3,4.193970004132387,1352.6776062531108,406.15,0.366495680809021,42.1852637639621,300000 |
| 39047.75,4.138045868900868,1838.0735508172133,548.75,0.4797986149787903,57.09954125038909,400000 |
| 49565.1,4.134912154456311,1820.352495718745,541.7,0.49860920906066897,56.555044049597335,500000 |
| 60737.1,4.17569670225439,1824.2937657342002,545.5,0.4913086771965027,56.67614352584495,600000 |
| 71472.25,4.206361895182486,1688.5022419907011,509.45,0.4693915367126465,52.503812693468525,700000 |
| 82120.65,4.02101291128791,1925.9573324739802,581.15,0.4998553991317749,59.799858632238326,800000 |
| 93448.8,4.26751102029504,1817.2801108191907,545.9,0.48604891300201414,56.46064194045275,900000 |
| 105020.4,4.185180430349914,1907.082585257597,572.65,0.5178009271621704,59.219913083405814,1000000 |
|
|
