Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / rlcode/reinforcement-learning issues and pull requests
#100 - Bump tensorflow from 1.0.0 to 1.15.4
Pull Request -
State: closed - Opened by dependabot[bot] about 4 years ago
- 1 comment
Labels: dependencies
#100 - Bump tensorflow from 1.0.0 to 1.15.4
Pull Request -
State: closed - Opened by dependabot[bot] about 4 years ago
- 1 comment
Labels: dependencies
#99 - Diagonal movement? - Grid Score
Issue -
State: open - Opened by karlstraube about 4 years ago
#99 - Diagonal movement? - Grid Score
Issue -
State: open - Opened by karlstraube about 4 years ago
#98 - Can this code run other atari game beside breakout?
Issue -
State: open - Opened by THSWind over 4 years ago
#98 - Can this code run other atari game beside breakout?
Issue -
State: open - Opened by THSWind over 4 years ago
#97 - A2C and A3C implementation
Pull Request -
State: open - Opened by juice1000 over 4 years ago
#97 - A2C and A3C implementation
Pull Request -
State: open - Opened by juice1000 over 4 years ago
#96 - How to run threading while using Keras and tensorflow
Issue -
State: open - Opened by Ayanamii-i over 4 years ago
#96 - How to run threading while using Keras and tensorflow
Issue -
State: open - Opened by Ayanamii-i over 4 years ago
#95 - issue regarding saved models
Issue -
State: open - Opened by chetanya230598 over 4 years ago
#95 - issue regarding saved models
Issue -
State: open - Opened by chetanya230598 over 4 years ago
#94 - Why are you using SARSA instead of Q-Learning?
Issue -
State: closed - Opened by laz8 over 4 years ago
- 1 comment
#94 - Why are you using SARSA instead of Q-Learning?
Issue -
State: closed - Opened by laz8 over 4 years ago
- 1 comment
#93 - Bump tensorflow from 1.0.0 to 1.15.2
Pull Request -
State: closed - Opened by dependabot[bot] almost 5 years ago
- 1 comment
Labels: dependencies
#93 - Bump tensorflow from 1.0.0 to 1.15.2
Pull Request -
State: closed - Opened by dependabot[bot] almost 5 years ago
- 1 comment
Labels: dependencies
#92 - Bump tensorflow from 1.0.0 to 1.15.0
Pull Request -
State: open - Opened by dependabot[bot] almost 5 years ago
#92 - Bump tensorflow from 1.0.0 to 1.15.0
Pull Request -
State: open - Opened by dependabot[bot] almost 5 years ago
#91 - Bump pillow from 4.1.0 to 6.2.0
Pull Request -
State: closed - Opened by dependabot[bot] about 5 years ago
- 1 comment
Labels: dependencies
#91 - Bump pillow from 4.1.0 to 6.2.0
Pull Request -
State: closed - Opened by dependabot[bot] about 5 years ago
- 1 comment
Labels: dependencies
#90 - The issue about breakout_a3c.py in 3-atari, when i execute source
Issue -
State: open - Opened by rhkatjd00 about 5 years ago
- 1 comment
#90 - The issue about breakout_a3c.py in 3-atari, when i execute source
Issue -
State: open - Opened by rhkatjd00 about 5 years ago
- 1 comment
#89 - reinforcement learning real life use cases
Issue -
State: open - Opened by palbha about 5 years ago
#89 - reinforcement learning real life use cases
Issue -
State: open - Opened by palbha about 5 years ago
#88 - Dqn-per does not use importance sampling weight in training。
Issue -
State: open - Opened by xunyiljg about 5 years ago
#88 - Dqn-per does not use importance sampling weight in training。
Issue -
State: open - Opened by xunyiljg about 5 years ago
#87 - Implementing policy gradient when number of output classes is large
Issue -
State: open - Opened by hoangcuong2011 almost 6 years ago
#87 - Implementing policy gradient when number of output classes is large
Issue -
State: open - Opened by hoangcuong2011 almost 6 years ago
#86 - update target_model before loading saved model in cartpole_dqn.py
Issue -
State: open - Opened by nyck33 almost 6 years ago
#86 - update target_model before loading saved model in cartpole_dqn.py
Issue -
State: open - Opened by nyck33 almost 6 years ago
#85 - Created Deep Recurrent Q-Network example
Pull Request -
State: open - Opened by Douglas-Cho almost 6 years ago
#85 - Created Deep Recurrent Q-Network example
Pull Request -
State: open - Opened by Douglas-Cho almost 6 years ago
#84 - Clean way to stop training
Pull Request -
State: open - Opened by AlexisBogroff about 6 years ago
- 1 comment
#84 - Clean way to stop training
Pull Request -
State: open - Opened by AlexisBogroff about 6 years ago
- 1 comment
#83 - How to add Dropout
Issue -
State: open - Opened by hoangcuong2011 about 6 years ago
#83 - How to add Dropout
Issue -
State: open - Opened by hoangcuong2011 about 6 years ago
#82 - is it possible to apply categorical_crossentropy to a3c?
Issue -
State: open - Opened by hhbyyh over 6 years ago
- 1 comment
#82 - is it possible to apply categorical_crossentropy to a3c?
Issue -
State: open - Opened by hhbyyh over 6 years ago
- 1 comment
#81 - rlcode.github.io does not exist !
Issue -
State: closed - Opened by yash-nisar over 6 years ago
#81 - rlcode.github.io does not exist !
Issue -
State: closed - Opened by yash-nisar over 6 years ago
#80 - A3C on GPU
Issue -
State: open - Opened by treksn over 6 years ago
#80 - A3C on GPU
Issue -
State: open - Opened by treksn over 6 years ago
#79 - Pong Policy Gradient-important error in the definition of the convolutional net.
Issue -
State: open - Opened by TomaszRem over 6 years ago
- 1 comment
#79 - Pong Policy Gradient-important error in the definition of the convolutional net.
Issue -
State: open - Opened by TomaszRem over 6 years ago
- 1 comment
#78 - Update README.md
Pull Request -
State: open - Opened by chenhang98 over 6 years ago
#78 - Update README.md
Pull Request -
State: open - Opened by chenhang98 over 6 years ago
#77 - Question on Policy Gradient
Issue -
State: closed - Opened by joaosalvado10 over 6 years ago
#77 - Question on Policy Gradient
Issue -
State: closed - Opened by joaosalvado10 over 6 years ago
#76 - couple a3c questions / recommendations for generalizing beyond Atari
Issue -
State: open - Opened by M00NSH0T almost 7 years ago
- 3 comments
#76 - couple a3c questions / recommendations for generalizing beyond Atari
Issue -
State: open - Opened by M00NSH0T almost 7 years ago
- 3 comments
#75 - Tutorial
Issue -
State: open - Opened by MyAusweis almost 7 years ago
#75 - Tutorial
Issue -
State: open - Opened by MyAusweis almost 7 years ago
#74 - The A2C carpole is wrong?
Issue -
State: closed - Opened by chenguandan almost 7 years ago
#74 - The A2C carpole is wrong?
Issue -
State: closed - Opened by chenguandan almost 7 years ago
#73 - Why use self.batch_size instead of batch_size
Issue -
State: open - Opened by JieMEI1994 almost 7 years ago
- 1 comment
#73 - Why use self.batch_size instead of batch_size
Issue -
State: open - Opened by JieMEI1994 almost 7 years ago
- 1 comment
#72 - Expected future rewards
Issue -
State: closed - Opened by naveen7v almost 7 years ago
- 1 comment
#71 - Use traned agent
Issue -
State: open - Opened by Sat0ri almost 7 years ago
#70 - Tensorflow A3C implementation gridworld environment
Pull Request -
State: open - Opened by akileshbadrinaaraayanan almost 7 years ago
#69 - save_graph dir was missing.
Pull Request -
State: open - Opened by hiroyachiba about 7 years ago
#68 - Add DQN with PER
Pull Request -
State: closed - Opened by jcwleo about 7 years ago
#67 - Saving QLearning Agent
Issue -
State: closed - Opened by mvrozanti about 7 years ago
#66 - Fail to converge for Breakout dqn
Issue -
State: open - Opened by yhcao6 about 7 years ago
- 4 comments
#65 - Training time of breakout-dqn
Issue -
State: closed - Opened by yhcao6 about 7 years ago
- 2 comments
#64 - Giving image as input in Gridworld
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 1 comment
#63 - Use of memory in Cartpole A3C
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
#62 - A3C for Gridworld
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
#61 - add comment on use of categorical_crossentropy
Pull Request -
State: closed - Opened by fredcallaway over 7 years ago
- 1 comment
#60 - Prioritized experience replay implementation
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 1 comment
#59 - Thank you for good materials!
Issue -
State: closed - Opened by hayoung-kim over 7 years ago
- 3 comments
#58 - Catastrophic collapse in episode score on cartpole_a3c
Issue -
State: open - Opened by erlendaxpo over 7 years ago
- 2 comments
#57 - Saved model usage
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 3 comments
#56 - My code is very poor in learning 2048 game using Double DQN
Issue -
State: open - Opened by codetiger over 7 years ago
- 2 comments
#55 - link was broken for the pong-a3c.py
Issue -
State: closed - Opened by kimbring2 over 7 years ago
- 1 comment
#54 - Add comment on the use of categorical cross entropy in REINFORCE and a2c
Issue -
State: open - Opened by fredcallaway over 7 years ago
- 9 comments
#53 - What each state signifies in Grid World
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 2 comments
#52 - Convergence
Issue -
State: closed - Opened by ShaniGam over 7 years ago
- 5 comments
#51 - Number of actions in deep SARSA grid world
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 2 comments
#50 - Clean up gridworld codes and add comments to reinforce code
Pull Request -
State: closed - Opened by Hyeokreal over 7 years ago
#49 - Batch size in A2C Cartpole
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 1 comment
#48 - Failing to converge with increase in grid-size (Grid World)
Issue -
State: open - Opened by akileshbadrinaaraayanan over 7 years ago
- 5 comments
#47 - Moving obstacles in Grid World
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 2 comments
#46 - installation guide updated
Pull Request -
State: closed - Opened by wooridle over 7 years ago
- 1 comment
#45 - Update cartpole_a2c.py
Pull Request -
State: closed - Opened by 20chase over 7 years ago
- 1 comment
#44 - Update cartpole_a2c.py
Pull Request -
State: closed - Opened by 20chase over 7 years ago
- 1 comment
#43 - Query regarding 'advantages' in a2c
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 4 comments
#42 - fix test file name
Pull Request -
State: closed - Opened by zzing0907 over 7 years ago
#41 - Reference links for each algorithm
Issue -
State: closed - Opened by akileshbadrinaaraayanan over 7 years ago
- 1 comment
#40 - create test file for breakout
Pull Request -
State: closed - Opened by zzing0907 over 7 years ago
- 1 comment
#39 - A3C algorithm - background
Issue -
State: closed - Opened by ShaniGam over 7 years ago
- 9 comments
#38 - fix gridworld deep-sarsa, reinforce
Pull Request -
State: closed - Opened by Hyeokreal over 7 years ago
#37 - Update breakout_ddqn.py
Pull Request -
State: closed - Opened by BlueMelon715 over 7 years ago
- 1 comment
#36 - play part
Issue -
State: closed - Opened by BlueMelon715 over 7 years ago
- 2 comments
#35 - Code Review & Refactoring
Pull Request -
State: closed - Opened by keon over 7 years ago
Labels: enhancement
#34 - fix defaultdict error
Pull Request -
State: closed - Opened by keon over 7 years ago
#33 - Readme Update
Pull Request -
State: closed - Opened by keon over 7 years ago
#32 - Code Cleanup!
Pull Request -
State: closed - Opened by keon over 7 years ago
- 1 comment
Labels: enhancement
#31 - Env BreakoutDeterministic-v4 not found
Issue -
State: closed - Opened by ShaniGam over 7 years ago
- 3 comments
#30 - module 'pandas' has no attribute 'computation'
Issue -
State: closed - Opened by sevenseablue over 7 years ago
#29 - sampling from deque
Issue -
State: closed - Opened by slakkur1 over 7 years ago
- 1 comment