astooke/rlpyt issues and pull requests

#100 - Iterating through namedarrytuple

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

#100 - Iterating through namedarrytuple

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

#99 - Alternatives to named(array)tuple?

Issue - State: closed - Opened by qxcv over 4 years ago - 13 comments

#99 - Alternatives to named(array)tuple?

Issue - State: closed - Opened by qxcv over 4 years ago - 13 comments

#98 - fix no attribute error which is thrown when using multi step return

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

#98 - fix no attribute error which is thrown when using multi step return

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

#97 - What is the minimum python version this codebase requires?

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

#97 - What is the minimum python version this codebase requires?

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

#96 - Some concerns over my results and benchmarks for DQN-based agents.

Issue - State: closed - Opened by DanielTakeshi over 4 years ago - 6 comments

#96 - Some concerns over my results and benchmarks for DQN-based agents.

Issue - State: closed - Opened by DanielTakeshi over 4 years ago - 6 comments

#95 - DQN algo: samples.action requires squeeze

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

#95 - DQN algo: samples.action requires squeeze

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

#94 - some explanation on BaseAgent.shared_model ?

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

#94 - some explanation on BaseAgent.shared_model ?

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

#93 - Bias in EvalCollector

Issue - State: open - Opened by kaixin96 over 4 years ago - 4 comments

#93 - Bias in EvalCollector

Issue - State: open - Opened by kaixin96 over 4 years ago - 4 comments

#92 - KeyError when using SyncRl runner

Issue - State: closed - Opened by kaixin96 over 4 years ago - 1 comment

#92 - KeyError when using SyncRl runner

Issue - State: closed - Opened by kaixin96 over 4 years ago - 1 comment

#91 - Can we use multiple GPUs for GPU sampler?

Issue - State: closed - Opened by kaixin96 over 4 years ago - 2 comments

#91 - Can we use multiple GPUs for GPU sampler?

Issue - State: closed - Opened by kaixin96 over 4 years ago - 2 comments

#90 - under parallel training mode, is statistic such as "StepsPerSecond" the overall data ?

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

#90 - under parallel training mode, is statistic such as "StepsPerSecond" the overall data ?

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

#89 - Fixed typo in logfile name

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

#89 - Fixed typo in logfile name

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

#88 - Support for weird graph-based observation data type

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

#88 - Support for weird graph-based observation data type

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

#87 - Working example code for R2D1

Issue - State: open - Opened by DavidMChan almost 5 years ago - 8 comments

#87 - Working example code for R2D1

Issue - State: open - Opened by DavidMChan almost 5 years ago - 8 comments

#86 - PPO alternating sampler example_3 error

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

#86 - PPO alternating sampler example_3 error

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

#85 - How can we train LSTM PPO?

Issue - State: closed - Opened by jd730 almost 5 years ago - 10 comments

#85 - How can we train LSTM PPO?

Issue - State: closed - Opened by jd730 almost 5 years ago - 10 comments

#84 - Is there any intention of implementing IMPALA?

Issue - State: closed - Opened by tarungog almost 5 years ago - 7 comments

#84 - Is there any intention of implementing IMPALA?

Issue - State: closed - Opened by tarungog almost 5 years ago - 7 comments

#83 - a question about the _action_set of "pong" game

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

#83 - a question about the _action_set of "pong" game

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

#82 - Tensorboard

Pull Request - State: closed - Opened by AlexanderKoch-Koch almost 5 years ago - 4 comments

#82 - Tensorboard

Pull Request - State: closed - Opened by AlexanderKoch-Koch almost 5 years ago - 4 comments

#81 - Which agent class should use when using PPO algorithm?

Issue - State: closed - Opened by codelast almost 5 years ago - 1 comment

#81 - Which agent class should use when using PPO algorithm?

Issue - State: closed - Opened by codelast almost 5 years ago - 1 comment

#80 - Consequences of Imprecise Space Definition?

Issue - State: closed - Opened by bpiv400 almost 5 years ago - 2 comments

#80 - Consequences of Imprecise Space Definition?

Issue - State: closed - Opened by bpiv400 almost 5 years ago - 2 comments

#79 - Training on CoinRun / ProcGen

Issue - State: closed - Opened by bmazoure almost 5 years ago - 9 comments

#79 - Training on CoinRun / ProcGen

Issue - State: closed - Opened by bmazoure almost 5 years ago - 9 comments

#78 - about nan in training process

Issue - State: closed - Opened by codelast almost 5 years ago - 3 comments

#78 - about nan in training process

Issue - State: closed - Opened by codelast almost 5 years ago - 3 comments

#77 - Tensorboard

Issue - State: closed - Opened by AlexanderKoch-Koch almost 5 years ago - 4 comments

#77 - Tensorboard

Issue - State: closed - Opened by AlexanderKoch-Koch almost 5 years ago - 4 comments

#76 - Batches with additional observations

Issue - State: open - Opened by bmazoure almost 5 years ago - 4 comments

#76 - Batches with additional observations

Issue - State: open - Opened by bmazoure almost 5 years ago - 4 comments

#75 - A2C derivative for mean is not implemented

Issue - State: closed - Opened by ThGravo almost 5 years ago - 9 comments

#75 - A2C derivative for mean is not implemented

Issue - State: closed - Opened by ThGravo almost 5 years ago - 9 comments

#74 - Using nvprof doesn't work

Issue - State: open - Opened by gauravjain14 almost 5 years ago - 6 comments

#74 - Using nvprof doesn't work

Issue - State: open - Opened by gauravjain14 almost 5 years ago - 6 comments

#73 - TypeError in loading optimizer parameters in ddpg

Issue - State: closed - Opened by renqibing almost 5 years ago - 3 comments

#73 - TypeError in loading optimizer parameters in ddpg

Issue - State: closed - Opened by renqibing almost 5 years ago - 3 comments

#72 - CPU resources, htop shows all 12 cores being used for example_1.py

Issue - State: closed - Opened by DanielTakeshi almost 5 years ago - 11 comments

#72 - CPU resources, htop shows all 12 cores being used for example_1.py

Issue - State: closed - Opened by DanielTakeshi almost 5 years ago - 11 comments

#71 - customized environment example?

Issue - State: closed - Opened by sufengniu almost 5 years ago - 6 comments

#71 - customized environment example?

Issue - State: closed - Opened by sufengniu almost 5 years ago - 6 comments

#70 - Added support for soft updates in DQN algo and agent.

Pull Request - State: closed - Opened by michalgregor almost 5 years ago - 1 comment

#70 - Added support for soft updates in DQN algo and agent.

Pull Request - State: closed - Opened by michalgregor almost 5 years ago - 1 comment

#69 - Pretrained models

Issue - State: open - Opened by juliusfrost almost 5 years ago - 11 comments

#69 - Pretrained models

Issue - State: open - Opened by juliusfrost almost 5 years ago - 11 comments

#68 - Making the multi-cpu single-gpu setup work on cluster

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

#68 - Making the multi-cpu single-gpu setup work on cluster

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

#67 - DQN with state vectors not frames

Issue - State: closed - Opened by ThGravo almost 5 years ago - 12 comments

#67 - DQN with state vectors not frames

Issue - State: closed - Opened by ThGravo almost 5 years ago - 12 comments

#66 - Are policy weights saved?

Issue - State: closed - Opened by thomasweng15 almost 5 years ago - 4 comments

#66 - Are policy weights saved?

Issue - State: closed - Opened by thomasweng15 almost 5 years ago - 4 comments

#65 - Logging outside of default location

Issue - State: closed - Opened by thomasweng15 almost 5 years ago - 2 comments

#65 - Logging outside of default location

Issue - State: closed - Opened by thomasweng15 almost 5 years ago - 2 comments

#64 - Sampler questions

Issue - State: closed - Opened by cambel almost 5 years ago - 4 comments

#64 - Sampler questions

Issue - State: closed - Opened by cambel almost 5 years ago - 4 comments

#63 - Passing arguments to env.reset() function without modifying the code in class SerialEvalCollector

Issue - State: closed - Opened by wiekern almost 5 years ago - 4 comments

#63 - Passing arguments to env.reset() function without modifying the code in class SerialEvalCollector

Issue - State: closed - Opened by wiekern almost 5 years ago - 4 comments

#62 - DistributedDataParallelCPU is deprecated

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

#62 - DistributedDataParallelCPU is deprecated

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

#61 - IndexError in SumTree.sample when unique=True

Issue - State: closed - Opened by wangwwno1 almost 5 years ago - 1 comment

#61 - IndexError in SumTree.sample when unique=True

Issue - State: closed - Opened by wangwwno1 almost 5 years ago - 1 comment

#60 - Where does horizon=27000 come from in atari_env.py ?

Issue - State: closed - Opened by codelast almost 5 years ago - 1 comment

#60 - Where does horizon=27000 come from in atari_env.py ?

Issue - State: closed - Opened by codelast almost 5 years ago - 1 comment

#59 - Issue #58 #61 Fix: Bug Fix & Perf. Optimize

Pull Request - State: closed - Opened by wangwwno1 almost 5 years ago - 4 comments

#59 - Issue #58 #61 Fix: Bug Fix & Perf. Optimize

Pull Request - State: closed - Opened by wangwwno1 almost 5 years ago - 4 comments

#58 - UnboundLocalError in replays/sequence/prioritized.py

Issue - State: closed - Opened by wangwwno1 almost 5 years ago - 2 comments

#58 - UnboundLocalError in replays/sequence/prioritized.py

Issue - State: closed - Opened by wangwwno1 almost 5 years ago - 2 comments

#57 - 'bootstrap_timelimit' in q function policy gradient algorithms

Issue - State: closed - Opened by renqibing almost 5 years ago - 3 comments

#57 - 'bootstrap_timelimit' in q function policy gradient algorithms

Issue - State: closed - Opened by renqibing almost 5 years ago - 3 comments

#56 - about variable/class/argument naming conventions

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

#56 - about variable/class/argument naming conventions

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

#55 - AttributeError: 'info' object has no attribute 'timeout' under Customed gym env wrapped by GymEnvWrapper

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

#55 - AttributeError: 'info' object has no attribute 'timeout' under Customed gym env wrapped by GymEnvWrapper

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

#54 - "no GPU AssertionError" should not be raised?

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

#54 - "no GPU AssertionError" should not be raised?

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

#53 - step_buffer_np not initialized in DecorrelatingStartCollector if max_decorrelation_steps == 0

Issue - State: closed - Opened by carlbalmer almost 5 years ago

#53 - step_buffer_np not initialized in DecorrelatingStartCollector if max_decorrelation_steps == 0

Issue - State: closed - Opened by carlbalmer almost 5 years ago

#52 - fixed bug in DecorrelatingStartCollector.start_envs

Pull Request - State: closed - Opened by carlbalmer almost 5 years ago - 1 comment

#52 - fixed bug in DecorrelatingStartCollector.start_envs

Pull Request - State: closed - Opened by carlbalmer almost 5 years ago - 1 comment

#51 - multi-modal observations of different length in one namedarraytuple

Issue - State: closed - Opened by carlbalmer almost 5 years ago - 1 comment

#51 - multi-modal observations of different length in one namedarraytuple

Issue - State: closed - Opened by carlbalmer almost 5 years ago - 1 comment

GitHub / astooke/rlpyt issues and pull requests