slm_lab/spec/benchmark/sac/sac_pong.json
{
"sac_pong": {
"agent": [{
"name": "SoftActorCritic",
"algorithm": {
"name": "SoftActorCritic",
"action_pdtype": "GumbelSoftmax",
"action_policy": "default",
"gamma": 0.99,
"training_start_step": 1000,
"training_frequency": 1
},
"memory": {
"name": "Replay",
"batch_size": 512,
"max_size": 1000000,
"use_cer": false
},
"net": {
"type": "ConvNet",
"shared": false,
"conv_hid_layers": [
[32, 8, 4, 0, 1],
[64, 4, 2, 0, 1],
[32, 3, 1, 0, 1]
],
"fc_hid_layers": [256, 256],
"hid_layers_activation": "leakyrelu",
"init_fn": "orthogonal_",
"normalize": true,
"batch_norm": true,
"clip_grad_val": 0.5,
"use_same_optim": false,
"loss_spec": {
"name": "SmoothL1Loss"
},
"optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 2.5e-4,
},
"lr_scheduler_spec": null,
"update_type": "polyak",
"update_frequency": 1,
"polyak_coef": 0.005,
"gpu": true
}
}],
"env": [{
"name": "PongNoFrameskip-v4",
"frame_op": "concat",
"frame_op_len": 4,
"reward_scale": "sign",
"num_envs": 4,
"max_t": null,
"max_frame": 1e6
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 100,
"eval_frequency": 100,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1,
}
}
}