Reinforcement Learning For Dialogue Systems 强化学习在对话系统中的应用 论文或开源应用总结
-
Updated
Dec 27, 2019
#
dyna-q
Here are 27 public repositories matching this topic...
Reinforcement Learning Algorithms in FrozenLake-v1
reinforcement-learning monte-carlo openai-gym q-learning reinforcement-learning-algorithms sarsa reinforce policy-iteration value-iteration td-learning actor-critic sarsa-lambda frozenlake frozenlake-v0 dyna-q sutton-gridworld monte-carlo-control sutton-barto-book
-
Updated
Feb 4, 2025 - Jupyter Notebook
PyTorch implementation of various reinforcement learning algorithms
-
Updated
Feb 22, 2018 - Python
reinforcement-learning q-learning sarsa gridworld multi-armed-bandits random-walk racecar bandit-algorithm sutton-book td-lambda dyna-q cliffwalking
-
Updated
Mar 4, 2020 - Python
ReLAx - Reinforcement Learning Applications Library
dqn ddpg sac trpo categorical-dqn ppo model-based-rl dyna-q reinforcementlearning td3 policy-gradients rainbow-dqn n-step-bootstrapping mbpo
-
Updated
Feb 19, 2023 - Python
path planning using Q learning algorithm
-
Updated
Oct 12, 2023 - Python
Reinforcement Learning Specialization courses solutions
reinforcement-learning neural-network monte-carlo q-learning policy-gradient sarsa markov-decision-processes temporal-differencing-learning dyna-q
-
Updated
Feb 2, 2022 - Jupyter Notebook
Reinforcement learning algorithms to solve OpenAI gym environments
reinforcement-learning openai-gym q-learning dqn cartpole mountain-car sarsa taxi openai-gym-environments frozenlake dyna-q
-
Updated
May 16, 2020 - Python
Various fundamental reinforcement learning algorithms implemented from scratch
python reinforcement-learning q-learning reinforcement-learning-algorithms sarsa expected-sarsa temporal-differencing-learning dyna-q prioritized-sweeping
-
Updated
May 26, 2020 - Python
Solving Markov Decision Process using Value Iteration and Policy Iteration, SARSA, Expected SARSA and Q-Learning
q-learning markov-decision-processes policy-iteration value-iteration expected-sarsa sarsa-learning dyna-q
-
Updated
Oct 20, 2021 - Jupyter Notebook
Assignments and Reading Material for RL Course
-
Updated
Mar 28, 2018 - Jupyter Notebook
Programming assignments completed for my Reinforcement Learning course: Topics include Bandit Algorithms, Dynamic Programming, policy iteration, Monte-Carlo methods, SARSA, Q-Learning, Dyna-Q/Dyna-Q+, gradient control methods, state aggregation methods, and Deep Q-Learning Networks (DQNs).
reinforcement-learning deep-learning monte-carlo deep-reinforcement-learning q-learning policy-gradient dynamic-programming deep-q-network policy-iteration gradient-descent-algorithm bandit-algorithms sarsa-learning dyna-q
-
Updated
Jan 28, 2023 - Jupyter Notebook
Implementation of all RL algorithms in a simpler way
reinforcement-learning qlearning monte-carlo reinforcement-learning-algorithms a3c monte-carlo-tree-search sac hierarchical-reinforcement-learning deep-q-learning trust-region-policy-optimization ddpg-algorithm a2c sarsa-learning dyna-q multi-agent-reinforcement-learning
-
Updated
Aug 29, 2025 - Jupyter Notebook
Homework for SJTU-AI3603.
-
Updated
Mar 28, 2026 - Python
Reinforcement Learning Using Q-learning, Double Q-learning, and Dyna-Q.
python reinforcement-learning q-learning gridworld transition-matrix probabilistic-model dyna-q deterministic-model
-
Updated
Oct 27, 2021 - Python
Experiments with Dyna-Q
-
Updated
Jul 29, 2024 - Jupyter Notebook
For this project, I created a reinforcement learning system. While learning about machine learning and designing structure, in which an object will learn by trail and error to produce the correct outcome.
python machine-learning reinforcement-learning algorithms numpy jupyter-notebook q-learning pandas sarsa matplotlib portfolio-project dyna-q
-
Updated
Dec 10, 2025 - Jupyter Notebook
Comparing RL algorithms for successful ghost capture of Pac-Man in a custom Gym environment.
python machine-learning reinforcement-learning deep-learning q-learning pytorch dqn sarsa gymnasium actor-critic model-training dyna-q
-
Updated
May 6, 2026
Model-Based Reinforcement Learning where the internal model is imperfect
-
Updated
Feb 15, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the dyna-q topic, visit your repo's landing page and select "manage topics."