File size: 2,909 Bytes
079c32c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from easydict import EasyDict

collector_env_num = 8
evaluator_env_num = 8
cartpole_r2d2_config = dict(
    exp_name='cartpole_r2d2_seed0',
    env=dict(
        collector_env_num=collector_env_num,
        evaluator_env_num=evaluator_env_num,
        n_evaluator_episode=evaluator_env_num,
        stop_value=195,
    ),
    policy=dict(
        cuda=False,
        priority=False,
        priority_IS_weight=False,
        model=dict(
            obs_shape=4,
            action_shape=2,
            encoder_hidden_size_list=[128, 128, 64],
        ),
        discount_factor=0.995,
        nstep=5,
        burnin_step=2,
        # (int) the whole sequence length to unroll the RNN network minus
        # the timesteps of burnin part,
        # i.e., <the whole sequence length> = <unroll_len> = <burnin_step> + <learn_unroll_len>
        learn_unroll_len=40,
        learn=dict(
            # according to the R2D2 paper, actor parameter update interval is 400
            # environment timesteps, and in per collect phase, we collect 32 sequence
            # samples, the length of each sample sequence is <burnin_step> + <unroll_len>,
            # which is 100 in our seeting, 32*100/400=8, so we set update_per_collect=8
            # in most environments
            update_per_collect=5,
            batch_size=64,
            learning_rate=0.0005,
            target_update_theta=0.001,
        ),
        collect=dict(
            # NOTE: It is important that set key traj_len_inf=True here,
            # to make sure self._traj_len=INF in serial_sample_collector.py.
            # In R2D2 policy, for each collect_env, we want to collect data of length self._traj_len=INF
            # unless the episode enters the 'done' state.
            # In each collect phase, we collect a total of <n_sample> sequence samples.
            n_sample=32,
            unroll_len=2 + 40,
            traj_len_inf=True,
            env_num=collector_env_num,
        ),
        eval=dict(env_num=evaluator_env_num, evaluator=dict(eval_freq=30)),
        other=dict(
            eps=dict(
                type='exp',
                start=0.95,
                end=0.05,
                decay=10000,
            ), replay_buffer=dict(replay_buffer_size=100000, )
        ),
    ),
)
cartpole_r2d2_config = EasyDict(cartpole_r2d2_config)
main_config = cartpole_r2d2_config
cartpole_r2d2_create_config = dict(
    env=dict(
        type='cartpole',
        import_names=['dizoo.classic_control.cartpole.envs.cartpole_env'],
    ),
    env_manager=dict(type='base'),
    policy=dict(type='r2d2'),
)
cartpole_r2d2_create_config = EasyDict(cartpole_r2d2_create_config)
create_config = cartpole_r2d2_create_config

if __name__ == "__main__":
    # or you can enter `ding -m serial -c cartpole_r2d2_config.py -s 0`
    from ding.entry import serial_pipeline
    serial_pipeline((main_config, create_config), seed=0)