Deep-Reinforcement-Learning-Hands-On
Hands-on Deep Reinforcement Learning, published by Packt
File Explorer
- 01_agent_anatomy.py
- 02_cartpole_random.py
- 03_random_actionwrapper.py
- 04_cartpole_random_monitor.py
- .gitignore
- 01_modules.py
- 02_tensorboard.py
- 03_atari_gan.py
- 01_cartpole.py
- 02_frozenlake_naive.py
- 03_frozenlake_tweaked.py
- 04_frozenlake_nonslippery.py
- 01_frozenlake_v_iteration.py
- 02_frozenlake_q_iteration.py
- __init__.py
- dqn_model.py
- wrappers.py
- 01_frozenlake_q_learning.py
- 02_dqn_pong.py
- 03_dqn_play.py
- commute.py
- distr_test.py
- prio_buffer_bench.py
- simple_buffer_bench.py
- __init__.py
- common.py
- dqn_model.py
- events.out.tfevents.1510382942.gpu
- events.out.tfevents.1510388189.gpu
- events.out.tfevents.1510390516.gpu
- events.out.tfevents.1510410396.gpu
- events.out.tfevents.1510410913.gpu
- events.out.tfevents.1510414458.gpu
- events.out.tfevents.1510417240.gpu
- events.out.tfevents.1510430593.gpu
- events.out.tfevents.1510437056.gpu
- .gitignore
- log-01_dqn_basic.py.txt
- log-02_dqn_n_steps.py.txt
- log-03_dqn_double.py.txt
- log-04_dqn_noisy_net.py.txt
- log-05_dqn_prio_replay.py.txt
- log-06_dqn_dueling.py.txt
- log-07_dqn_distrib.py.txt
- log-08_dqn_rainbow.py.txt
- 01_dqn_basic.py
- 02_dqn_n_steps.py
- 03_dqn_double.py
- 04_dqn_noisy_net.py
- 05_dqn_prio_replay.py
- 06_dqn_dueling.py
- 07_dqn_distrib.py
- 08_dqn_rainbow.py
- ch08-small-quotes.tgz
- unpack_data.sh
- __init__.py
- common.py
- data.py
- environ.py
- models.py
- validation.py
- test_data.py
- test_environ.py
- .gitignore
- run_model.py
- train_model.py
- train_model_conv.py
- __init__.py
- common.py
- events.out.tfevents.1512126826.gpu
- events.out.tfevents.1512299794.gpu
- events.out.tfevents.1512305287.gpu
- events.out.tfevents.1512572754.gpu
- 01_cartpole_dqn.py
- 02_cartpole_reinforce.py
- 03_cartpole_reinforce_baseline.py
- 04_cartpole_pg.py
- 05_pong_pg.py
- __init__.py
- common.py
- 00_pong_pg-loc-baseline.py
- 00_pong_pg.py
- .gitignore
- 01_cartpole_pg.py
- 02_pong_a2c.py
- 03_pong_a2c_rollouts.py
- 04_pong_r2.py
- log.md
- distr_grad.py
- distr_grad2.py
- sync_bench.py
- __init__.py
- common.py
- .gitignore
- 01_a3c_data.py
- 02_a3c_grad.py
- .gitignore
- get_data.sh
- __init__.py
- cornell.py
- data.py
- model.py
- utils.py
- test_data.py
- test_subtitles.py
- .gitignore
- cor_reader.py
- data_test.py
- telergam_bot.py
- train_crossent.py
- train_scst.py
- use_model.py
- demo_dump.py
- fbs_dump.py
- fbs_join.py
- fbs_read.py
- start_docker.sh
- start_docker_demo.sh
- wd_tests.py
- wob_clicks.py
- wob_create.py
- wob_test.py
- demo-CountSides.tar.gz
- demo-TicTacToe.tgz
- fbs.ksy
- rfp_client.ksy
- rfp_server.ksy
- __init__.py
- fbs.py
- rfp_client.py
- rfp_server.py
- __init__.py
- common.py
- model_vnc.py
- vnc_demo.py
- wob_vnc.py
- 01_wob_crash-fix.patch
- 02_reward_proxy_append_rewards.patch
- autopatch.sh
- readme.md
- .gitignore
- environment.yml
- wob_click_mm_play.py
- wob_click_mm_train.py
- wob_click_play.py
- wob_click_train.py
- record_a2c.sh
- record_ddpg.sh
- __init__.py
- common.py
- model.py
- .gitignore
- 01_check_env.py
- 02_train_a2c.py
- 03_play_a2c.py
- 04_train_ddpg.py
- 05_play_ddpg.py
- 06_train_d4pg.py
- __init__.py
- common.py
- kfac.py
- model.py
- trpo.py
- .gitignore
- 01_train_a2c.py
- 02_play.py
- 03_train_trpo.py
- 04_train_ppo.py
- 05_train_acktr.py
- 02_breakout_es.py
- 02_hyper.py
- .gitignore
- 01_cartpole_es.py
- 02_cheetah_es.py
- 03_cartpole_ga.py
- 04_cheetah_ga.py
- 05_cheetah_ga_batch.py
- __init__.py
- common.py
- i2a.py
- .gitignore
- 01_a2c.py
- 02_imag.py
- 03_i2a.py
- play.py
- __init__.py
- game.py
- mcts.py
- model.py
- __init__.py
- test_game.py
- test_model.py
- charts-checkpoint.ipynb
- charts.ipynb
- .gitignore
- play.py
- semi-final.sh
- telegram-bot.py
- train.py
- ch01-01.eps
- ch01-02.eps
- ch01-03.eps
- ch01.pdf
- ch04-01.eps
- ch04-02.eps
- ch04-03.eps
- ch04-04.eps
- ch04-05.eps
- ch04-06.eps
- ch04-07.eps
- ch04.pdf
- ch05-001.eps
- ch05-002.eps
- ch05-003.eps
- ch05-004.eps
- ch05-005.eps
- ch05-006.eps
- ch05-007.eps
- ch05-008.eps
- ch05-009.eps
- ch05-010.eps
- ch05-011.eps
- ch05-012.eps
- ch05-013.eps
- ch05-014.eps
- ch05-015.eps
- ch05-016.eps
- ch05-017.eps
- ch05-018.eps
- ch05-019.eps
- ch05-020.eps
- ch05-021.eps
- ch05-022.eps
- ch05-023.eps
- ch05-024.eps
- ch05-025.eps
- ch05-026.eps
- ch05-027.eps
- ch05-028.eps
- ch05-029.eps
- ch05-030.eps
- ch05-031.eps
- ch05-032.eps
- ch05-033.eps
- ch05-034.eps
- ch05-035.eps
- ch05-036.eps
- ch05-037.eps
- ch05-038.eps
- ch05-039.eps
- ch05-040.eps
- ch05-041.eps
- ch05-042.eps
- ch05-043.eps
- ch05-044.eps
- ch05-045.eps
- ch05-046.eps
- ch05-047.eps
- ch05-048.eps
- ch05-049.eps
- ch05-050.eps
- ch05-051.eps
- ch05-052.eps
- ch05-053.eps
- ch05-054.eps
- ch05-055.eps
- ch05-056.eps
- ch05-057.eps
- ch05-058.eps
- ch05-059.eps
- ch05-060.eps
- ch05-061.eps
- ch05-062.eps
- ch05-063.eps
- ch05-064.eps
- ch05-065.eps
- ch05-066.eps
- ch05-067.eps
- ch05-068.eps
- ch05.pdf
- ch06-001.eps
- ch06-002.eps
- ch06-003.eps
- ch06-004.eps
- ch06-005.eps
- ch06-006.eps
- ch06-007.eps
- ch06-008.eps
- ch06-009.eps
- ch06-010.eps
- ch06-011.eps
- ch06-012.eps
- ch06-013.eps
- ch06-014.eps
- ch06-015.eps
- ch06.pdf
- ch07-001.eps
- ch07-002.eps
- ch07-003.eps
- ch07-004.eps
- ch07-005.eps
- ch07-006.eps
- ch07-007.eps
- ch07-008.eps
- ch07-009.eps
- ch07-010.eps
- ch07-011.eps
- ch07-012.eps
- ch07-013.eps
- ch07.pdf
- ch09-001.eps
- ch09-002.eps
- ch09-003.eps
- ch09-004.eps
- ch09-005.eps
- ch09-006.eps
- ch09-007.eps
- ch09-008.eps
- ch09-009.eps
- ch09-010.eps
- ch09.pdf
- ch10-001.eps
- ch10-002.eps
- ch10-003.eps
- ch10-004.eps
- ch10-005.eps
- ch10-006.eps
- ch10-007.eps
- ch10-008.eps
- ch10-009.eps
- ch10-010.eps
- ch10-011.eps
- ch10-012.eps
- ch10-013.eps
- ch10-014.eps
- ch10-015.eps
- ch10.pdf
- ch12-001.eps
- ch12-002.eps
- ch12-003.eps
- ch12-004.eps
- ch12-005.eps
- ch12.pdf
- ch14-001.eps
- ch14-002.eps
- ch14-003.eps
- ch14-004.eps
- ch14-005.eps
- ch14-006.eps
- ch14-007.eps
- ch14-008.eps
- ch14-009.eps
- ch14-010.eps
- ch14-011.eps
- ch14-012.eps
- ch14-013.eps
- ch14-014.eps
- ch14-015.eps
- ch14-016.eps
- ch14-017.eps
- ch14-018.eps
- ch14-019.eps
- ch14-020.eps
- ch14-021.eps
- ch14-022.eps
- ch14-023.eps
- ch14-024.eps
- ch14.pdf
- ch15-001.eps
- ch15-002.eps
- ch15-003.eps
- ch15-004.eps
- ch15-005.eps
- ch15-006.eps
- ch15-007.eps
- ch15-008.eps
- ch15-009.eps
- ch15-010.eps
- ch15-011.eps
- ch15-012.eps
- ch15-013.eps
- ch15-014.eps
- ch15-015.eps
- ch15-016.eps
- ch15-017.eps
- ch15-018.eps
- ch15-019.eps
- ch15-020.eps
- ch15.pdf
- ch16-001.eps
- ch16-002.eps
- ch16-003.eps
- ch16-004.eps
- ch16-005.eps
- ch16-006.eps
- ch16-007.eps
- ch16-008.eps
- ch16-009.eps
- ch16-010.eps
- ch16-011.eps
- ch16-012.eps
- ch16-013.eps
- ch16-014.eps
- ch16-015.eps
- ch16-016.eps
- ch16-017.eps
- ch16-018.eps
- ch16-019.eps
- ch16-020.eps
- ch16-021.eps
- ch16-022.eps
- ch16.pdf
- ch18-001.eps
- ch18-002.eps
- ch18-003.eps
- ch18-004.eps
- ch18-005.eps
- ch18-006.eps
- ch18-007.eps
- ch18-008.eps
- ch18-009.eps
- ch18.pdf
- .gitignore
- _template.tex
- ch01.tex
- ch04.tex
- ch05.tex
- ch06.tex
- ch07.tex
- ch09.tex
- ch10.tex
- ch12.tex
- ch14.tex
- ch15.tex
- ch16.tex
- ch18.tex
- clean.sh
- make.sh
- .gitignore
- download-roboschool.sh
- install-roboschool.sh
- LICENSE
- README.md
- requirements.txt
# Installation Guide
pythonPrerequisites
- Python 3.6
- PyTorch 0.4.1
- pip
- OpenAI Gym
Setup Steps
pip install -r requirements.txt
Install python package dependencies required for the project.
python Chapter02/02_cartpole_random.py
Run a specific chapter's example python script.
Key Commands
pip install -r requirements.txt
Installs the required libraries specified in requirements.txt.
python Chapter06/02_dqn_pong.py
Runs the reinforcement learning agent training or execution script.
Some environments (e.g., Chapter 13) may require Roboschool and additional environment setup.
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Link
Example
// repository documentation
Was this content helpful?
(0 ratings)
