slm_lab/spec/benchmark/a2c/a2c_gae_unity.json
{
"a2c_gae_unitybasic": {
"agent": [{
"name": "A2C",
"algorithm": {
"name": "ActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"explore_var_spec": null,
"gamma": 0.99,
"lam": 0.95,
"num_step_returns": null,
"entropy_coef_spec": {
"name": "no_decay",
"start_val": 0.01,
"end_val": 0.01,
"start_step": 0,
"end_step": 0
},
"val_loss_coef": 1.0,
"training_frequency": 64
},
"memory": {
"name": "OnPolicyBatchReplay",
},
"net": {
"type": "MLPNet",
"shared": false,
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"batch_norm": false,
"clip_grad_val": 0.5,
"use_same_optim": false,
"loss_spec": {
"name": "MSELoss"
},
"actor_optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 3e-4,
},
"critic_optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"gpu": false
}
}],
"env": [{
"name": "${env}",
"frame_op": "concat",
"frame_op_len": 4,
"num_envs": 1,
"max_t": 10000,
"max_frame": 2e6
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1
},
"spec_params": {
"env": [
"Unity3DBall-v0",
"Unity3DBallHard-v0",
"UnityHallway-v0",
"UnityPushBlock-v0",
"UnityPyramids-v0"
]
}
},
"a2c_gae_unityadv": {
"agent": [{
"name": "A2C",
"algorithm": {
"name": "ActorCritic",
"action_pdtype": "default",
"action_policy": "default",
"explore_var_spec": null,
"gamma": 0.99,
"lam": 0.95,
"num_step_returns": null,
"entropy_coef_spec": {
"name": "no_decay",
"start_val": 0.01,
"end_val": 0.01,
"start_step": 0,
"end_step": 0
},
"val_loss_coef": 1.0,
"training_frequency": 64
},
"memory": {
"name": "OnPolicyBatchReplay",
},
"net": {
"type": "MLPNet",
"shared": false,
"hid_layers": [256, 256],
"hid_layers_activation": "relu",
"init_fn": "orthogonal_",
"batch_norm": false,
"clip_grad_val": 0.5,
"use_same_optim": false,
"loss_spec": {
"name": "MSELoss"
},
"actor_optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 3e-4,
},
"critic_optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 3e-4,
},
"lr_scheduler_spec": null,
"gpu": false
}
}],
"env": [{
"name": "${env}",
"frame_op": "concat",
"frame_op_len": 4,
"num_envs": 1,
"max_t": 10000,
"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": [
"UnityCrawlerDynamic-v0",
"UnityCrawlerStatic-v0",
"UnityReacher-v0",
"UnityWalker-v0"
]
}
}
}