1e9c3ee592be5e11dcce932a73009488d6f85474,ch17/03_i2a.py,,,#,18
Before Change
obs_shape = envs[0].observation_space.shape
act_n = envs[0].action_space.n
net_policy = common.AtariA2C(obs_shape, act_n)
net_em = i2a.EnvironmentModel(obs_shape, act_n)
net_em.load_state_dict(torch.load(args.em, map_location=lambda storage, loc: storage))
net_i2a = i2a.I2A(obs_shape, act_n, net_em, net_policy, ROLLOUTS_STEPS)
if args.cuda:
net_policy.cuda()
net_em.cuda()
net_i2a.cuda()
print(net_i2a)
obs = envs[0].reset()
obs_v = ptan.agent.default_states_preprocessor([obs], cuda=args.cuda)
After Change
obs_shape = envs[0].observation_space.shape
act_n = envs[0].action_space.n
net_policy = common.AtariA2C(obs_shape, act_n).to(device)
net_em = i2a.EnvironmentModel(obs_shape, act_n)
net_em.load_state_dict(torch.load(args.em, map_location=lambda storage, loc: storage))
net_em = net_em.to(device)
net_i2a = i2a.I2A(obs_shape, act_n, net_em, net_policy, ROLLOUTS_STEPS).to(device)
print(net_i2a)
obs = envs[0].reset()
obs_v = ptan.agent.default_states_preprocessor([obs]).to(device)
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 6
Instances
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/03_i2a.py
Class Name:
Method Name:
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 9e80c11073af48db2876fc943df9264a7ab0488e
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch11/02_a3c_grad.py
Class Name:
Method Name:
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/01_a2c.py
Class Name:
Method Name: