slm_lab/spec/benchmark/sac/sac_roboschool.json
{
"sac_roboschool": {
"agent": [{
"name": "SoftActorCritic",
"algorithm": {
"name": "SoftActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"gamma": 0.99,
"training_frequency": 1
},
"memory": {
"name": "Replay",
"batch_size": 256,
"max_size": 1000000,
"use_cer": true
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"clip_grad_val": 1.0,
"loss_spec": {
"name": "MSELoss"
},
"optim_spec": {
"name": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"update_type": "polyak",
"update_frequency": 1,
"polyak_coef": 0.005,
"gpu": false
}
}],
"env": [{
"name": "${env}",
"num_envs": 8,
"max_t": null,
"max_frame": 2e6
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1
},
"spec_params": {
"env": [
"RoboschoolAnt-v1", "RoboschoolAtlasForwardWalk-v1", "RoboschoolHalfCheetah-v1", "RoboschoolHopper-v1", "RoboschoolInvertedDoublePendulum-v1", "RoboschoolInvertedPendulum-v1", "RoboschoolReacher-v1", "RoboschoolWalker2d-v1"
]
}
},
"sac_humanoid": {
"agent": [{
"name": "SoftActorCritic",
"algorithm": {
"name": "SoftActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"gamma": 0.99,
"training_frequency": 1
},
"memory": {
"name": "Replay",
"batch_size": 256,
"max_size": 1000000,
"use_cer": true
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"clip_grad_val": 1.0,
"loss_spec": {
"name": "MSELoss"
},
"optim_spec": {
"name": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"update_type": "polyak",
"update_frequency": 1,
"polyak_coef": 0.005,
"gpu": false
}
}],
"env": [{
"name": "RoboschoolHumanoid-v1",
"num_envs": 8,
"max_t": null,
"max_frame": 5e6
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1
}
},
"sac_humanoidflagrun": {
"agent": [{
"name": "SoftActorCritic",
"algorithm": {
"name": "SoftActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"gamma": 0.99,
"training_frequency": 1
},
"memory": {
"name": "Replay",
"batch_size": 256,
"max_size": 1000000,
"use_cer": true
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"clip_grad_val": 1.0,
"loss_spec": {
"name": "MSELoss"
},
"optim_spec": {
"name": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"update_type": "polyak",
"update_frequency": 1,
"polyak_coef": 0.005,
"gpu": false
}
}],
"env": [{
"name": "RoboschoolHumanoidFlagrun-v1",
"num_envs": 8,
"max_t": null,
"max_frame": 1e7
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1
}
},
"sac_humanoidflagrunharder": {
"agent": [{
"name": "SoftActorCritic",
"algorithm": {
"name": "SoftActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"gamma": 0.99,
"training_frequency": 1
},
"memory": {
"name": "Replay",
"batch_size": 256,
"max_size": 1000000,
"use_cer": true
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"clip_grad_val": 1.0,
"loss_spec": {
"name": "MSELoss"
},
"optim_spec": {
"name": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"update_type": "polyak",
"update_frequency": 1,
"polyak_coef": 0.005,
"gpu": false
}
}],
"env": [{
"name": "RoboschoolHumanoidFlagrunHarder-v1",
"num_envs": 8,
"max_t": null,
"max_frame": 1e7
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1
}
}
}