dennybritz/reinforcement-learning issues and pull requests

#252 - MC Control with Epsilon-Greedy Policies ---Epsilon Value and Best Action prob error

Issue - State: open - Opened by hardik-kansal 11 months ago - 2 comments

#251 - create new file

Pull Request - State: closed - Opened by iw4p over 1 year ago

#250 - demystifying-deep-reinforcement-learning link is broken

Issue - State: open - Opened by kiankyars over 1 year ago

#249 - Create index.html

Pull Request - State: closed - Opened by dkavargy over 1 year ago - 1 comment

#248 - Update README.md

Pull Request - State: open - Opened by pajjaecat over 1 year ago

#247 - please provide requirements.txt or mention the exact version of packages used.

Issue - State: open - Opened by Nahdus almost 2 years ago

#246 - Issue in: reinforcement-learning/MC/MC Prediction Solution.ipynb

Issue - State: open - Opened by Almujtaba-Yaseen about 2 years ago

#245 - Fixed compatibility with current version of OpenAI gym without DiscreteEnv class

Pull Request - State: closed - Opened by arielsboiardi about 2 years ago - 1 comment

#244 - Typo in: "Model-Free Prediction & Control with Monte Carlo (MC)" section -> "Blackjack Playground.ipynb" file:

Issue - State: open - Opened by Almujtaba-Yaseen about 2 years ago

#243 - A small correction in "MDPs and Bellman Equations" section

Issue - State: open - Opened by Almujtaba-Yaseen over 2 years ago

#242 - Modify "v (list) : state value function" to "V"

Pull Request - State: open - Opened by hslyu about 3 years ago

#241 - Hello

Pull Request - State: open - Opened by simplephi about 3 years ago

#240 - Update README.md

Pull Request - State: open - Opened by hardlyhuman about 3 years ago

#239 - Minor Link fix

Issue - State: open - Opened by gitDawn about 3 years ago

#238 - Reinforcement learning policy

Issue - State: open - Opened by Comp-Engr18 over 3 years ago - 1 comment

#237 - Error 'show() takes 1 positional argument but 2 were given' fixed in plotting.py

Pull Request - State: open - Opened by Dolores2333 almost 4 years ago

#236 - DQN Testing Rewards on Atari Games

Issue - State: closed - Opened by willtop almost 4 years ago - 1 comment

#235 - Clarification on DQN testing rewards on Atari games

Issue - State: open - Opened by willtop almost 4 years ago

#234 - Minor fixes

Pull Request - State: open - Opened by rafardenas almost 4 years ago

#233 - update slides

Pull Request - State: open - Opened by harsh306 about 4 years ago - 1 comment

#232 - Lecture Slides need an update

Issue - State: open - Opened by harsh306 about 4 years ago

#231 - Monte Carlo AssertionError: defaultdict(<function mc_control_importance_sampling.<locals>.<lambda> at 0x7f31699ffe18>, {}) (<class 'collections.defaultdict'>)

Issue - State: open - Opened by NC25 over 4 years ago

#230 - Update DP exercise policy evaluation solution

Pull Request - State: closed - Opened by gorkemkrdmn over 4 years ago

#229 - Policy Evaluation Exercise Solution Is Wrong

Issue - State: closed - Opened by gorkemkrdmn over 4 years ago - 1 comment

#228 - Delete init.py

Pull Request - State: closed - Opened by dtlics over 4 years ago - 1 comment

#227 - DQL size error

Issue - State: open - Opened by johan606303 over 4 years ago

#226 - added: Double DQN Proportional Prioritized Experience Replay Solution

Pull Request - State: open - Opened by makaveli10 over 4 years ago - 2 comments

#225 - added: DoubleDQN Proportional Prioritized Replay solution

Pull Request - State: closed - Opened by makaveli10 over 4 years ago

#224 - Some question in MC Control with Epsilon-Greedy Policies Solution.ipynb

Issue - State: closed - Opened by josephbak over 4 years ago - 2 comments

#223 - Gambler's Problem: 0 Stake Allowed?

Issue - State: open - Opened by mparigi over 4 years ago - 1 comment

#222 - why DQN use kernel size 8 ?

Issue - State: open - Opened by opentld almost 5 years ago

#221 - Why is Chapter 11 excluded?

Issue - State: open - Opened by BedirT almost 5 years ago - 2 comments

#220 - Is a line missing in 'MC Control with Epsilon-Greedy Policies Solution.ipynb'?

Issue - State: open - Opened by Ritz111 almost 5 years ago - 1 comment

#219 - Why CliffWalkingEnv returns 'is_done=True' when reaching cliff?

Issue - State: closed - Opened by wakamori almost 5 years ago - 2 comments

#218 - Can an agent learn valid actions offline, being able to choose only actions that were already taken (e.g. from historical data) ? [question]

Issue - State: open - Opened by WalterEren almost 5 years ago - 6 comments

#217 - Deep Q Learning, neither works with tensorflow 1.x nor with tensorflow 2.x

Issue - State: open - Opened by azharsalman about 5 years ago - 1 comment

#216 - Update README.md

Pull Request - State: closed - Opened by roshray about 5 years ago - 1 comment

#215 - Mdp branch

Pull Request - State: closed - Opened by csxiang18 about 5 years ago

#214 - a test pull req (corrected few typos)

Pull Request - State: closed - Opened by nsydn about 5 years ago - 1 comment

#213 - Could anyone show me reason why use 4 same grayscale frames when training DQN?

Issue - State: closed - Opened by roachsinai about 5 years ago - 1 comment

#212 - Policy iteration solution only show 1 optimal solution

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

#208 - log

Issue - State: open - Opened by Mahsa-Bastankhah over 5 years ago

#207 - Exercise notebooks with no outputs.

Pull Request - State: open - Opened by avullo over 5 years ago

#206 - Add Links to Deepnote

Pull Request - State: open - Opened by jirkalhotka over 5 years ago

#205 - Test the policy in "Value Iteration" exercise

Pull Request - State: open - Opened by link2xt over 5 years ago - 1 comment

#204 - Provided policy_improvement() solution initializes values to zero for each iteration

Issue - State: open - Opened by link2xt over 5 years ago - 2 comments

#203 - Provided policy_improvement() solution is not guaranteed to terminate

Issue - State: open - Opened by link2xt over 5 years ago - 1 comment

#202 - policy_improvement() should be renamed to policy_iteration()

Issue - State: open - Opened by link2xt over 5 years ago

#201 - Update CliffWalk REINFORCE with Baseline Solution.ipynb

Pull Request - State: closed - Opened by guotong1988 over 5 years ago - 1 comment

#200 - Vanilla REINFORCE implementation

Issue - State: open - Opened by alek5k over 5 years ago - 2 comments

#199 - Q-Learning docstring improvements.

Pull Request - State: closed - Opened by anuzis over 5 years ago - 1 comment

#198 - Fix rendering crash on Win 10

Pull Request - State: closed - Opened by fspirit over 5 years ago - 2 comments

#197 - Proposal of Expected SARSA algorithm

Pull Request - State: open - Opened by AntonioSerrano over 5 years ago - 1 comment

#196 - Randomness in optimal epsilon_greedy_policy

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

#195 - Updated links to new version of Sutton and Barto's book

Pull Request - State: closed - Opened by PieroMacaluso over 5 years ago - 1 comment

#194 - fixed shape descriptions for neural network input layer

Pull Request - State: closed - Opened by alek5k over 5 years ago - 1 comment

#193 - Add link to Advanced Depp Learning & Reinforcement Learning lectures.

Pull Request - State: closed - Opened by fspirit over 5 years ago - 1 comment

#192 - Unstable reinforce with baseline model

Issue - State: open - Opened by Jacobi93 almost 6 years ago - 2 comments

#191 - Home

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

#190 - feed action to critic network

Issue - State: open - Opened by ehsaneshaghi almost 6 years ago

#189 - How to restore model

Issue - State: open - Opened by tdr1991 almost 6 years ago

#188 - cleaning up lib/envs/gridword.py

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

#187 - updates to README.md

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

#186 - The output layer should not using RELU activation function.

Issue - State: open - Opened by wanjunhong0 almost 6 years ago

#185 - You don't follow the book?

Issue - State: open - Opened by alexmosc about 6 years ago

#184 - Why RBFSampler from sklearn is used as the feature in the FA example?

Issue - State: closed - Opened by zyongxu about 6 years ago

#183 - DQN Dense Tensor Using too Much Memory

Issue - State: closed - Opened by nflu about 6 years ago - 1 comment

#182 - Blackjack - Monte Carlo Prediction

Issue - State: open - Opened by rahulptel about 6 years ago - 1 comment

#181 - Policy Gradient Methods: Loss function of policy estimator in REINFORCE

Issue - State: closed - Opened by ArikVoronov about 6 years ago - 3 comments

#180 - Batch update for Continuous Mountain Car Actor-Critic

Issue - State: open - Opened by GoingMyWay about 6 years ago - 1 comment

#179 - Define an envirement

Issue - State: open - Opened by ewtrends about 6 years ago

#178 - Adding k-bandit implementation

Pull Request - State: open - Opened by rae83 about 6 years ago

#177 - policy evaluation algorithm and implementation bug

Issue - State: closed - Opened by Hamifthi about 6 years ago - 6 comments

#176 - Update README.md

Pull Request - State: closed - Opened by suraj2596 about 6 years ago

#175 - added link to CS885

Pull Request - State: closed - Opened by shar1pius about 6 years ago - 1 comment

#174 - [bug] DQN/dqn.py: Incorrect loss function. [question] Question about RMSProp paramethers

Issue - State: open - Opened by Kropekk about 6 years ago - 5 comments

#173 - OSError: [Errno 12] Cannot allocate memory

Issue - State: open - Opened by VictorLeeLk over 6 years ago - 2 comments

#172 - Questionable result in Gamblers Problem Solution

Issue - State: open - Opened by bminixhofer over 6 years ago - 12 comments

#171 - Policy Evaluation Solution VS Sutton's Page 75

Issue - State: closed - Opened by benjamintanweihao over 6 years ago - 1 comment

#170 - Is the Implementation correct?

Issue - State: closed - Opened by Nerdyvedi over 6 years ago

#169 - Create MDP_David_class_first_example.py

Pull Request - State: open - Opened by olmerg over 6 years ago

#168 - Continuous MountainCar Actor Critic issue

Issue - State: open - Opened by zhouPengF over 6 years ago

#167 - Policy Gradient, when action space is 40, how can I sample action from Gaussian?

Issue - State: open - Opened by GoingMyWay over 6 years ago

#166 - Modify Policy Evaluation Solution.ipynb according to David Silver's slides.

Pull Request - State: open - Opened by QikeLi over 6 years ago - 1 comment

#160 - OSError: [Errno 12] Cannot allocate memory

Issue - State: closed - Opened by sklf over 6 years ago

#159 - Reset BlackjackEnv to a chosen state

Issue - State: open - Opened by enpassanty over 6 years ago - 1 comment

#156 - issue with value update function

Issue - State: open - Opened by gskishan004 over 6 years ago - 6 comments

#152 - Does anyone know why I can not import lib in jupyter notebook?

Issue - State: closed - Opened by aiot-tech over 6 years ago - 6 comments

#151 - Unclear what gather_indices holds

Issue - State: closed - Opened by aneesh297 over 6 years ago - 2 comments

#149 - A problem in MC Prediction Solution

Issue - State: open - Opened by dslwz2008 over 6 years ago - 5 comments

#141 - ffmpeg problem - CalledProcessError: Command '['ffmpeg', '-version']' returned non-zero exit status -6

Issue - State: open - Opened by digiamm almost 7 years ago - 1 comment

#131 - No module named lib.envs.gridworld

Issue - State: open - Opened by PsyberLearns almost 7 years ago - 2 comments

#116 - What's the difference between baseline solution and Actor-Critic

Issue - State: open - Opened by droiter about 7 years ago - 5 comments

#107 - Workaround for environment max step limit of 200.

Pull Request - State: open - Opened by sedand about 7 years ago - 6 comments

#104 - activation fn from relu to None

Pull Request - State: closed - Opened by 404akhan over 7 years ago - 1 comment

GitHub / dennybritz/reinforcement-learning issues and pull requests