(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,373 gym INFO <0.00> Environment reset
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,398 gym INFO <0.00> === STARTING STEP ===
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,398 sats.satellite.RSO INFO <0.00> RSO: action_downlink tasked for 1000000000.0 seconds
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,398 sats.satellite.RSO INFO <0.00> RSO: setting timed terminal event at 1000000000.0
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,399 sats.satellite.Inspector-1 INFO <0.00> Inspector-1: Thrust clamped from 1.5812388639479453 m/s to 1.0 m/s.
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,399 sats.satellite.Inspector-1 INFO <0.00> Inspector-1: Thrusting with inertial dV [-0.69845299 -0.40948755 0.58692705] with 9424.12109375 second drift.
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,399 sats.satellite.Inspector-1 INFO <0.00> Inspector-1: setting timed terminal event at 9424.1
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,399 sats.satellite.Inspector-1 INFO <0.00> Inspector-1: FSW action action_inspect_rso activated.
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,411 sats.satellite.Inspector-1 INFO <435.00> Inspector-1: Exceeded maximum range of 1000 m from RSO
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,461 data.rso_inspection INFO <435.00> Inspected/Illuminated/Total: 0/32/100
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,462 data.base INFO <435.00> Total reward: {}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,462 sats.satellite.Inspector-1 WARNING <435.00> Inspector-1: failed range_valid check
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,464 gym INFO <435.00> Step reward: {'Inspector-1': np.float64(-1.0)}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,464 gym INFO <435.00> Episode terminated: ['Inspector-1']
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,466 gym INFO <435.00> === STARTING STEP ===
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,466 sats.satellite.RSO INFO <435.00> RSO: action_downlink tasked for 1000000000.0 seconds
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,466 sats.satellite.RSO INFO <435.00> RSO: setting timed terminal event at 1000000435.0
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:10,701 sats.satellite.Inspector-1 INFO <9425.00> Inspector-1: timed termination at 9424.1
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,131 data.rso_inspection INFO <9425.00> Inspected/Illuminated/Total: 0/77/100
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,131 data.base INFO <9425.00> Total reward: {}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,131 sats.satellite.Inspector-1 INFO <9425.00> Inspector-1: Satellite Inspector-1 requires retasking
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,132 gym INFO <9425.00> Step reward: {}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,133 gym INFO <9425.00> === STARTING STEP ===
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,133 sats.satellite.RSO INFO <9425.00> RSO: action_downlink tasked for 1000000000.0 seconds
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:11,133 sats.satellite.RSO INFO <9425.00> RSO: setting timed terminal event at 1000009425.0
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:14,517 data.rso_inspection INFO <57000.00> Inspected/Illuminated/Total: 0/78/100
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:14,517 data.base INFO <57000.00> Total reward: {}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:14,517 gym INFO <57000.00> Step reward: {}
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:14,517 gym INFO <57000.00> Episode terminated: ['RSO']
(MultiAgentEnvRunner pid=47902) 2025-06-25 14:26:14,517 gym INFO <57000.00> Episode truncated: ['RSO']
Describe the bug
May be an RLlib issue.
To Reproduce