epoch 0001 learning_rate 0x3951b717 0.00019999999494757503
epoch 0001 policy_loss 0xba954440 -0.0011388137936592102
epoch 0001 value_loss 0x3891b048 6.9469737354666e-05
epoch 0001 entropy 0x4070739c 3.75705623626709
epoch 0001 total_loss 0xbd1e694d -0.03867464140057564
epoch 0001 old_approx_kl 0xba506a00 -0.0007950365543365479
epoch 0001 approx_kl 0x36190000 2.2798776626586914e-06
epoch 0001 clipfrac 0x00000000 0.0
epoch 0001 importance 0x3f801a20 1.0007972717285156
epoch 0001 weight proj_in.weight torch.float32 (8, 8268) 9c536525899eda1ad86426ffcceb6adddc6a668a1eddd19c15de5d49d893d185
epoch 0001 weight proj_in.bias torch.float32 (8,) 883ddd18c770946320053960d0005c426a0efea77f7b898ec3fbf9e1501e92d4
epoch 0001 weight cell.weight_ih torch.float32 (24, 8) 7f7c2c288bc1e04f90010660cd5c417d90f6ccf1373fb3a598754e388aa1d1ac
epoch 0001 weight cell.weight_hh torch.float32 (24, 8) 3e23341b4720c1758660e8d3e656344c74d4c6dae759153bf05a3f0cba149f22
epoch 0001 weight cell.bias_ih torch.float32 (24,) a8c03b99c5ff674bda4144c69c4529a0080856d7ee11ef8a683378468f16e947
epoch 0001 weight cell.bias_hh torch.float32 (24,) 5318fca84ab412799bbfe2b5922529662711b9a446b666ecc764601e9c61bde5
epoch 0001 weight actor.0.weight torch.float32 (8, 8) e5b937f4872bbc113980e0d63b72fc806b113270b3ae4fded501ab3d4dfd28e5
epoch 0001 weight actor.0.bias torch.float32 (8,) 2807cf90e31ba525f70bd66fa253a0c5b6118a1963482510cb7a5c445663ef57
epoch 0001 weight actor.1.weight torch.float32 (43, 8) bbbf4ee5e094338837ac35fcc96310cd10a5095b80832ecd03c80502be8ab29b
epoch 0001 weight actor.1.bias torch.float32 (43,) 8534d07aca36206009ec5b0a7988a82e3a2f25cf2f42f01df5bdfbecbfc5b276
epoch 0001 weight critic.0.weight torch.float32 (8, 8) ba86e7a5547e19cc5fde46d35f879c1423b2112fbb1a7bb8666767498363a036
epoch 0001 weight critic.0.bias torch.float32 (8,) 6aff2a9a5f8667c94de7626f0803ddf4b7e9c555bd38c8efd54a3cdf2595ec48
epoch 0001 weight critic.1.weight torch.float32 (1, 8) 23844a729281614342fb722e67e026bdc09630917d14980d41e23542c45d5737
epoch 0001 weight critic.1.bias torch.float32 (1,) 6515a389b6da2b3943fdc640396c788e567a9f38f9e22cc1ed721a456136ef82
