├── .gitignore ├── 1. DQN ├── README.md ├── agent.py ├── main.py ├── models │ └── dqn_q_20240712092431.pth └── test.py ├── 2. Double-DQN ├── README.md ├── agent.py ├── main.py ├── models │ └── double_dqn_q_20240712101605.pth └── test.py ├── 3. Dueling-DQN ├── README.md ├── agent.py ├── main.py ├── models │ └── dueling_dqn_q_20240712123003.pth └── test.py ├── 4. Noisy-DQN ├── README.md ├── agent.py ├── main.py ├── models │ └── noisy_dqn_q_20250321094856.pth └── test.py ├── 5. DDPG ├── README.md ├── agent.py ├── main.py ├── models │ └── ddpg_actor_20250320224131.pth └── test.py ├── 6. PPO-Discrete ├── README.md ├── agent.py ├── main.py ├── models │ └── ppo_actor_20250320230032.pth └── test.py ├── 7. PPO-Continuous ├── README.md ├── agent.py ├── main.py ├── models │ └── ppo_policy_20250320232933.pth ├── normalization.py └── test.py ├── 8. SAC ├── README.md ├── agent.py ├── main.py ├── models │ └── sac_actor_20250320211156.pth └── test.py ├── README.md ├── STUDY_NOTE.md ├── common ├── README.md ├── __init__.py └── tools.py └── images ├── baseline.png ├── continuous-1.png ├── continuous-2.png ├── credit.png ├── curiosity.png ├── ddpg_re.png ├── double_dqn_re.png ├── dqn-game.png ├── dqn.png ├── dqn_re.png ├── dueling-dqn-1.png ├── dueling-dqn.png ├── dueling_dqn_re.png ├── exploration.png ├── icon.png ├── multi-step.png ├── noisy-net.png ├── noisy_dqn_re.png ├── ppo.png ├── ppo_c_re.png ├── ppo_d_re.png ├── prioritized-replay.png ├── q.png ├── rainbow-1.png ├── rainbow-2.png ├── sac.png ├── sampling.png ├── sparse-reward.png ├── target.png └── td.png /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/.gitignore -------------------------------------------------------------------------------- /1. DQN/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /1. DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/1. DQN/agent.py -------------------------------------------------------------------------------- /1. DQN/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/1. DQN/main.py -------------------------------------------------------------------------------- /1. DQN/models/dqn_q_20240712092431.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/1. DQN/models/dqn_q_20240712092431.pth -------------------------------------------------------------------------------- /1. DQN/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/1. DQN/test.py -------------------------------------------------------------------------------- /2. Double-DQN/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/2. Double-DQN/README.md -------------------------------------------------------------------------------- /2. Double-DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/2. Double-DQN/agent.py -------------------------------------------------------------------------------- /2. Double-DQN/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/2. Double-DQN/main.py -------------------------------------------------------------------------------- /2. Double-DQN/models/double_dqn_q_20240712101605.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/2. Double-DQN/models/double_dqn_q_20240712101605.pth -------------------------------------------------------------------------------- /2. Double-DQN/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/2. Double-DQN/test.py -------------------------------------------------------------------------------- /3. Dueling-DQN/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/3. Dueling-DQN/README.md -------------------------------------------------------------------------------- /3. Dueling-DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/3. Dueling-DQN/agent.py -------------------------------------------------------------------------------- /3. Dueling-DQN/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/3. Dueling-DQN/main.py -------------------------------------------------------------------------------- /3. Dueling-DQN/models/dueling_dqn_q_20240712123003.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/3. Dueling-DQN/models/dueling_dqn_q_20240712123003.pth -------------------------------------------------------------------------------- /3. Dueling-DQN/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/3. Dueling-DQN/test.py -------------------------------------------------------------------------------- /4. Noisy-DQN/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /4. Noisy-DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/4. Noisy-DQN/agent.py -------------------------------------------------------------------------------- /4. Noisy-DQN/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/4. Noisy-DQN/main.py -------------------------------------------------------------------------------- /4. Noisy-DQN/models/noisy_dqn_q_20250321094856.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/4. Noisy-DQN/models/noisy_dqn_q_20250321094856.pth -------------------------------------------------------------------------------- /4. Noisy-DQN/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/4. Noisy-DQN/test.py -------------------------------------------------------------------------------- /5. DDPG/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /5. DDPG/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/5. DDPG/agent.py -------------------------------------------------------------------------------- /5. DDPG/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/5. DDPG/main.py -------------------------------------------------------------------------------- /5. DDPG/models/ddpg_actor_20250320224131.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/5. DDPG/models/ddpg_actor_20250320224131.pth -------------------------------------------------------------------------------- /5. DDPG/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/5. DDPG/test.py -------------------------------------------------------------------------------- /6. PPO-Discrete/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /6. PPO-Discrete/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/6. PPO-Discrete/agent.py -------------------------------------------------------------------------------- /6. PPO-Discrete/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/6. PPO-Discrete/main.py -------------------------------------------------------------------------------- /6. PPO-Discrete/models/ppo_actor_20250320230032.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/6. PPO-Discrete/models/ppo_actor_20250320230032.pth -------------------------------------------------------------------------------- /6. PPO-Discrete/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/6. PPO-Discrete/test.py -------------------------------------------------------------------------------- /7. PPO-Continuous/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /7. PPO-Continuous/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/7. PPO-Continuous/agent.py -------------------------------------------------------------------------------- /7. PPO-Continuous/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/7. PPO-Continuous/main.py -------------------------------------------------------------------------------- /7. PPO-Continuous/models/ppo_policy_20250320232933.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/7. PPO-Continuous/models/ppo_policy_20250320232933.pth -------------------------------------------------------------------------------- /7. PPO-Continuous/normalization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/7. PPO-Continuous/normalization.py -------------------------------------------------------------------------------- /7. PPO-Continuous/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/7. PPO-Continuous/test.py -------------------------------------------------------------------------------- /8. SAC/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /8. SAC/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/8. SAC/agent.py -------------------------------------------------------------------------------- /8. SAC/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/8. SAC/main.py -------------------------------------------------------------------------------- /8. SAC/models/sac_actor_20250320211156.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/8. SAC/models/sac_actor_20250320211156.pth -------------------------------------------------------------------------------- /8. SAC/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/8. SAC/test.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /STUDY_NOTE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/STUDY_NOTE.md -------------------------------------------------------------------------------- /common/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/common/README.md -------------------------------------------------------------------------------- /common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /common/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/common/tools.py -------------------------------------------------------------------------------- /images/baseline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/baseline.png -------------------------------------------------------------------------------- /images/continuous-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/continuous-1.png -------------------------------------------------------------------------------- /images/continuous-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/continuous-2.png -------------------------------------------------------------------------------- /images/credit.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/credit.png -------------------------------------------------------------------------------- /images/curiosity.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/curiosity.png -------------------------------------------------------------------------------- /images/ddpg_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/ddpg_re.png -------------------------------------------------------------------------------- /images/double_dqn_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/double_dqn_re.png -------------------------------------------------------------------------------- /images/dqn-game.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dqn-game.png -------------------------------------------------------------------------------- /images/dqn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dqn.png -------------------------------------------------------------------------------- /images/dqn_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dqn_re.png -------------------------------------------------------------------------------- /images/dueling-dqn-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dueling-dqn-1.png -------------------------------------------------------------------------------- /images/dueling-dqn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dueling-dqn.png -------------------------------------------------------------------------------- /images/dueling_dqn_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/dueling_dqn_re.png -------------------------------------------------------------------------------- /images/exploration.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/exploration.png -------------------------------------------------------------------------------- /images/icon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/icon.png -------------------------------------------------------------------------------- /images/multi-step.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/multi-step.png -------------------------------------------------------------------------------- /images/noisy-net.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/noisy-net.png -------------------------------------------------------------------------------- /images/noisy_dqn_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/noisy_dqn_re.png -------------------------------------------------------------------------------- /images/ppo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/ppo.png -------------------------------------------------------------------------------- /images/ppo_c_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/ppo_c_re.png -------------------------------------------------------------------------------- /images/ppo_d_re.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/ppo_d_re.png -------------------------------------------------------------------------------- /images/prioritized-replay.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/prioritized-replay.png -------------------------------------------------------------------------------- /images/q.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/q.png -------------------------------------------------------------------------------- /images/rainbow-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/rainbow-1.png -------------------------------------------------------------------------------- /images/rainbow-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/rainbow-2.png -------------------------------------------------------------------------------- /images/sac.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/sac.png -------------------------------------------------------------------------------- /images/sampling.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/sampling.png -------------------------------------------------------------------------------- /images/sparse-reward.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/sparse-reward.png -------------------------------------------------------------------------------- /images/target.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/target.png -------------------------------------------------------------------------------- /images/td.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cloudpetticoats/deep-reinforcement-learning/HEAD/images/td.png --------------------------------------------------------------------------------