Hugging Face's logo

OpenDILabCommunity
/
Pendulum-v1-TD3

Reinforcement Learning
PyTorch
English
deep-reinforcement-learning
DI-engine
Pendulum-v1
Model card Files Community
Pendulum-v1-TD3
File size: 3,043 Bytes 
54e54cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
 
exp_config = {
    'env': {
        'manager': {
            'episode_num': float("inf"),
            'max_retry': 1,
            'retry_type': 'reset',
            'auto_reset': True,
            'step_timeout': None,
            'reset_timeout': None,
            'retry_waiting_time': 0.1,
            'cfg_type': 'BaseEnvManagerDict'
        },
        'stop_value': -250,
        'collector_env_num': 8,
        'evaluator_env_num': 5,
        'act_scale': True,
        'n_evaluator_episode': 5
    },
    'policy': {
        'model': {
            'twin_critic': True,
            'obs_shape': 3,
            'action_shape': 1,
            'action_space': 'regression'
        },
        'learn': {
            'learner': {
                'train_iterations': 1000000000,
                'dataloader': {
                    'num_workers': 0
                },
                'log_policy': True,
                'hook': {
                    'load_ckpt_before_run': '',
                    'log_show_after_iter': 100,
                    'save_ckpt_after_iter': 10000,
                    'save_ckpt_after_run': True
                },
                'cfg_type': 'BaseLearnerDict'
            },
            'update_per_collect': 2,
            'batch_size': 128,
            'learning_rate_actor': 0.001,
            'learning_rate_critic': 0.001,
            'ignore_done': True,
            'target_theta': 0.005,
            'discount_factor': 0.99,
            'actor_update_freq': 2,
            'noise': True,
            'noise_sigma': 0.1,
            'noise_range': {
                'min': -0.5,
                'max': 0.5
            }
        },
        'collect': {
            'collector': {
                'collect_print_freq': 1000
            },
            'unroll_len': 1,
            'noise_sigma': 0.1,
            'n_sample': 48
        },
        'eval': {
            'evaluator': {
                'eval_freq': 100,
                'render': {
                    'render_freq': -1,
                    'mode': 'train_iter'
                },
                'cfg_type': 'InteractionSerialEvaluatorDict',
                'n_episode': 5,
                'stop_value': -250
            }
        },
        'other': {
            'replay_buffer': {
                'replay_buffer_size': 20000
            }
        },
        'on_policy': False,
        'cuda': False,
        'multi_gpu': False,
        'bp_update_sync': True,
        'traj_len_inf': False,
        'type': 'td3',
        'priority': False,
        'priority_IS_weight': False,
        'random_collect_size': 800,
        'transition_with_policy_data': False,
        'action_space': 'continuous',
        'reward_batch_norm': False,
        'multi_agent': False,
        'cfg_type': 'TD3PolicyDict'
    },
    'exp_name': 'Pendulum-v1-TD3',
    'seed': 0,
    'wandb_logger': {
        'gradient_logger': True,
        'video_logger': True,
        'plot_logger': True,
        'action_logger': True,
        'return_logger': False
    }
}