PacktPublishing/Deep-Reinforcement-Learning-Hands-On issues and pull requests

#50 - Chapter08: exploration in the validation procedure, is it an issue ?

Issue - State: closed - Opened by domixit over 5 years ago - 1 comment

#49 - Chapter 14: DDPG Agent instead of D4PG

Issue - State: closed - Opened by Phlogiston90 over 5 years ago - 1 comment

#49 - Chapter 14: DDPG Agent instead of D4PG

Issue - State: closed - Opened by Phlogiston90 over 5 years ago - 1 comment

#48 - Chapter07/lib/common.py - definitions for a newbie

Issue - State: open - Opened by jeffCabrera0321 over 5 years ago

#47 - tensorboard first example problem

Issue - State: closed - Opened by mettinger over 5 years ago - 4 comments

#46 - Chapter08 - run_model.py return size mismatch

Issue - State: closed - Opened by lamhk over 5 years ago - 2 comments

#45 - Chapter 11: 02_a3c_grad.py

Issue - State: open - Opened by JTatts over 5 years ago

#44 - chapter09 PG_baseline_cartpole

Issue - State: open - Opened by charles-bu over 5 years ago

#43 - dqn_play.py for Chapter07

Issue - State: closed - Opened by dorjeduck over 5 years ago - 3 comments

#42 - Possible bug in Chapter08/lib/data.py

Issue - State: closed - Opened by educob over 5 years ago - 2 comments

#41 - Multi-agent D4PG

Issue - State: closed - Opened by canteli over 5 years ago - 2 comments

#40 - importing env Chapter 13

Issue - State: closed - Opened by icompute386 over 5 years ago

#39 - Effect of larger sample queue?

Issue - State: closed - Opened by icompute386 over 5 years ago - 2 comments

#38 - Saving/Running Model from 08_dqn_rainbow.py

Issue - State: closed - Opened by icompute386 over 5 years ago

#37 - Purpose of new_state = new_state

Issue - State: closed - Opened by icompute386 over 5 years ago - 1 comment

#36 - Chapter 6 Problem/Bug? On 02_dqn_pong.py

Issue - State: closed - Opened by icompute386 over 5 years ago - 4 comments

#35 - Converting to support GPU

Issue - State: closed - Opened by icompute386 over 5 years ago - 3 comments

#34 - A3C grad_paralell gradients addition

Issue - State: closed - Opened by gowtham1997 over 5 years ago

#33 - A3C Bug?

Issue - State: closed - Opened by gowtham1997 over 5 years ago - 2 comments

#32 - CUDA performance of training code, Chapter 8, much lower than expected

Issue - State: open - Opened by Transigent over 5 years ago - 2 comments

#31 - Chapter07/04_dqn_noisy_net.py stability

Issue - State: closed - Opened by davidcotton over 5 years ago

#30 - Update 02_pong_a2c.py

Pull Request - State: closed - Opened by puppetect over 5 years ago

#29 - Chapter 7: 03_dqn_double.py

Issue - State: closed - Opened by JTatts over 5 years ago - 2 comments

#28 - RuntimeError in wob_click_play.py

Issue - State: open - Opened by hemanthsavasere over 5 years ago - 1 comment

#27 - Chapter13: wob_click_train.py not getting 0.8 mean reward even after 200k

Issue - State: open - Opened by hemanthsavasere over 5 years ago

#26 - Fix minor typo in NoisyFactorizedLinear

Pull Request - State: closed - Opened by davidcotton over 5 years ago

#25 - Chapter06/02_dqn_pong.py can't learn properly after modified the ScaleFloatFrame

Issue - State: closed - Opened by liuyuezhang over 5 years ago - 1 comment

#24 - Upgrade tensorboardX to 1.6 to avoid failure without cuda

Pull Request - State: closed - Opened by glasslion over 5 years ago

#23 - 02_pong_a2c.py not working with argument --cuda

Issue - State: closed - Opened by iimmer over 5 years ago - 3 comments

#22 - chapter 12: 'torch.dtype' object has no attribute 'type'

Issue - State: closed - Opened by NewEnglandML over 5 years ago - 4 comments

#21 - Chapter 7: What is the use of eq_mask?

Issue - State: closed - Opened by gowtham1997 over 5 years ago - 1 comment

#20 - Chapter 8: How to load data for continuation of training

Issue - State: closed - Opened by jeffCabrera0321 over 5 years ago - 1 comment

#19 - tensorboard error

Issue - State: closed - Opened by psusmit almost 6 years ago - 1 comment

#18 - Chapter 6: dqn_pong Confusing statement

Issue - State: closed - Opened by gowtham1997 almost 6 years ago - 2 comments

#17 - Ch. 15 Trpo algorithm's implementation: get_kl method

Issue - State: closed - Opened by lanseyege almost 6 years ago - 2 comments

#16 - Chapter 18: difference from original paper

Issue - State: closed - Opened by ryuoujisinta almost 6 years ago - 1 comment

#15 - Normalise Gym video frames between [-1, 1]

Pull Request - State: closed - Opened by gowtham1997 almost 6 years ago - 2 comments

#14 - calulation of Q in chapter 6 pong

Issue - State: closed - Opened by autohandle almost 6 years ago - 1 comment

#13 - Fix indexation in D4PG implementations

Pull Request - State: closed - Opened by Shmuma almost 6 years ago

#12 - Fix issue #11, pytorch compatibility

Pull Request - State: closed - Opened by Shmuma almost 6 years ago

#11 - Ch. 17 lib/i2a.py using tensor with wrong type as an index

Issue - State: closed - Opened by stevenapsel almost 6 years ago - 1 comment

#10 - How to reload the models in Chapter07?

Issue - State: closed - Opened by javabean68 almost 6 years ago - 4 comments

#9 - Advantage computation fix - Chapter 8 models.py

Pull Request - State: closed - Opened by Sycor4x almost 6 years ago - 1 comment

GitHub / PacktPublishing/Deep-Reinforcement-Learning-Hands-On issues and pull requests