slm_lab/spec/benchmark/dqn/ddqn_per_unity.json
{
"ddqn_per_unitybasic": {
"agent": [{
"name": "DoubleDQN",
"algorithm": {
"name": "DoubleDQN",
"action_pdtype": "Argmax",
"action_policy": "epsilon_greedy",
"explore_var_spec": {
"name": "linear_decay",
"start_val": 1.0,
"end_val": 0.01,
"start_step": 0,
"end_step": 50000
},
"gamma": 0.99,
"training_batch_iter": 1,
"training_iter": 1,
"training_frequency": 1,
"training_start_step": 64
},
"memory": {
"name": "PrioritizedReplay",
"alpha": 0.6,
"epsilon": 0.0001,
"batch_size": 64,
"max_size": 200000,
"use_cer": false,
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 128],
"hid_layers_activation": "relu",
"clip_grad_val": 10.0,
"loss_spec": {
"name": "SmoothL1Loss"
},
"optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 2.5e-4
},
"lr_scheduler_spec": null,
"update_type": "replace",
"update_frequency": 100,
"gpu": false
}
}],
"env": [{
"name": "${env}",
"frame_op": "concat",
"frame_op_len": 4,
"num_envs": 1,
"max_t": 10000,
"max_frame": 2e6
}],
"body": {
"product": "outer",
"num": 1
},
"meta": {
"distributed": false,
"log_frequency": 1000,
"eval_frequency": 1000,
"rigorous_eval": 0,
"max_session": 4,
"max_trial": 1,
},
"spec_params": {
"env": [
"Unity3DBall-v0",
"Unity3DBallHard-v0",
"UnityHallway-v0",
"UnityPushBlock-v0",
"UnityPyramids-v0"
]
}
},
"ddqn_per_unityadv": {
"agent": [{
"name": "DoubleDQN",
"algorithm": {
"name": "DoubleDQN",
"action_pdtype": "Argmax",
"action_policy": "epsilon_greedy",
"explore_var_spec": {
"name": "linear_decay",
"start_val": 1.0,
"end_val": 0.01,
"start_step": 0,
"end_step": 50000
},
"gamma": 0.99,
"training_batch_iter": 1,
"training_iter": 1,
"training_frequency": 1,
"training_start_step": 64
},
"memory": {
"name": "PrioritizedReplay",
"alpha": 0.6,
"epsilon": 0.0001,
"batch_size": 64,
"max_size": 200000,
"use_cer": false,
},
"net": {
"type": "MLPNet",
"hid_layers": [256, 128],
"hid_layers_activation": "relu",
"clip_grad_val": 10.0,
"loss_spec": {
"name": "SmoothL1Loss"
},
"optim_spec": {
"name": "Lookahead",
"optimizer": "RAdam",
"lr": 2.5e-4
},
"lr_scheduler_spec": null,
"update_type": "replace",
"update_frequency": 100,
"gpu": false
}
}],
"env": [{
"name": "${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"
]
}
}
}