Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / google-deepmind/acme issues and pull requests

#97 - Training a single agent with multiple GPUs

Issue - State: closed - Opened by ineuron over 3 years ago - 1 comment

#96 - Acme with Reverb?

Issue - State: closed - Opened by DriesSmit almost 4 years ago

#95 - ModuleNotFoundError: No module named 'acme.environment_loops'

Issue - State: closed - Opened by DriesSmit almost 4 years ago - 12 comments

#94 - Adding (optional) checkpointing for reverb replays

Pull Request - State: closed - Opened by filangelos almost 4 years ago - 1 comment
Labels: cla: yes

#93 - from acme.adders import reverb as adders not working

Issue - State: closed - Opened by yashvirsinghgrewal-crypto almost 4 years ago - 2 comments

#92 - Intuition behind layer normalization

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

#91 - examples.gym.helpers is missing

Issue - State: closed - Opened by edran almost 4 years ago

#90 - Unable to load Facebook NetHack NLE

Issue - State: open - Opened by MauriceManning almost 4 years ago - 5 comments
Labels: question

#88 - Refactored the Code and improved the Code Quality and Performance

Pull Request - State: closed - Opened by HarshCasper almost 4 years ago
Labels: cla: yes

#87 - Add OpenSpiel interface

Pull Request - State: closed - Opened by jhtschultz almost 4 years ago - 16 comments
Labels: cla: yes

#86 - Fixing Code Quality and Performance Issues

Pull Request - State: closed - Opened by HarshCasper almost 4 years ago - 5 comments
Labels: cla: yes

#84 - Contribute new logger?

Issue - State: closed - Opened by kamil-kaczmarek about 4 years ago - 5 comments

#83 - Minor error in the file: acme/examples/tutorial.ipynb

Issue - State: closed - Opened by jSieber7 about 4 years ago

#82 - D4PG actor behavior network's Gaussian noise exploration clipped to -1 and 1

Issue - State: closed - Opened by colingwuyu about 4 years ago - 2 comments

#81 - PyPI tf-nightly version incompatible

Issue - State: closed - Opened by colingwuyu about 4 years ago - 3 comments

#80 - [Feature] OpenSpiel integration/support

Issue - State: closed - Opened by lanctot about 4 years ago - 3 comments

#79 - R2D2 support for continuous (Bounded) environments

Issue - State: closed - Opened by chrispoulin about 4 years ago - 2 comments

#78 - Concatenation of observations with actions fails

Issue - State: closed - Opened by notreadyyet about 4 years ago - 3 comments

#77 - GPU Usage Too Much

Issue - State: closed - Opened by yiwc about 4 years ago - 1 comment

#76 - Float 64 precision

Issue - State: closed - Opened by yiwc about 4 years ago - 1 comment

#75 - Save and Load Agent

Issue - State: closed - Opened by yiwc about 4 years ago - 1 comment

#74 - Problem with SequenceAdder and reverb adders test_utils

Issue - State: closed - Opened by RaoulDrake about 4 years ago - 2 comments

#73 - DDPG: Add observation_network and target_observation_network to checkpointer.

Pull Request - State: closed - Opened by PPSantos about 4 years ago - 1 comment
Labels: cla: yes

#72 - DQN Agent's Snapshot Directory

Issue - State: open - Opened by ThomasBuffagni about 4 years ago - 1 comment

#71 - [Multi-agent][feature request] Acme multi-agent support

Issue - State: closed - Opened by DanielWicz about 4 years ago - 5 comments

#70 - CSV Logger does not close files.

Issue - State: closed - Opened by aacorn about 4 years ago - 6 comments

#69 - R2D3 Agent sets up Priority Table with Uniform Sampling

Issue - State: closed - Opened by weichseltree about 4 years ago - 1 comment

#68 - Distributed Workers - Question

Issue - State: closed - Opened by jeffreywillert about 4 years ago - 5 comments

#67 - How implement decaying epsilon greedy policy (DQN agent)

Issue - State: closed - Opened by nicola-pesavento about 4 years ago - 1 comment

#66 - run_dqfd.py error

Issue - State: closed - Opened by yiwc about 4 years ago - 1 comment

#64 - Do ACME developers plan to support the PyTorch library?

Issue - State: closed - Opened by erfanMhi about 4 years ago - 1 comment

#63 - installation of acme reverb according to instructions fails on MacOS 10.14.6

Issue - State: closed - Opened by yanvirin about 4 years ago - 1 comment

#62 - FeedForwardActor does not support tfd.Distribution output

Issue - State: closed - Opened by Kmeco about 4 years ago - 1 comment

#61 - Use tensorflow probability JAX substrate to standardize the implementations

Issue - State: closed - Opened by joaogui1 about 4 years ago - 1 comment

#60 - dm_contol env.seed, reward/action normalization, and acme.wrapper

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

#59 - Non-Mandatory CSVLogger UID (or custom UID)?

Issue - State: closed - Opened by RylanSchaeffer over 4 years ago - 2 comments
Labels: enhancement

#58 - Questions re: Custom Distributional Agents in ACME?

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

#57 - D4PG's vmin and vmax paramaters

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

#56 - Policy update in D4PG

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

#55 - Tracking Memory Consumption?

Issue - State: closed - Opened by alejandroarmas over 4 years ago - 12 comments
Labels: bug

#54 - Training become extremely slow after 20k steps

Issue - State: closed - Opened by ARISES-Phase2 over 4 years ago - 4 comments
Labels: question

#53 - Acme agents hyperparameters

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

#52 - dm_control environments and difference with dm_env

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

#50 - documentation for IMPALA

Issue - State: closed - Opened by yuvaramsingh94 over 4 years ago - 3 comments

#49 - Saving and restoring model/network

Issue - State: closed - Opened by vishnukmd7 over 4 years ago - 1 comment

#48 - [Error] Acme cannot build on ppc64le

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

#46 - How to modify acme.adders.reverb.base.Adder for adding several environments' transitions in Acme?

Issue - State: open - Opened by fmxFranky over 4 years ago - 8 comments
Labels: question

#45 - DQN crashes on tensorflow 2.3rc

Issue - State: closed - Opened by honglu2875 over 4 years ago - 2 comments

#44 - Using annealing epsilon greedy policy

Issue - State: closed - Opened by honglu2875 over 4 years ago - 2 comments

#43 - Agent evaluation and results

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

#42 - Padded sequences in running Impala

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

#41 - NLP

Issue - State: closed - Opened by chrislouis0106 over 4 years ago - 5 comments

#40 - Overlapping sequences vs. period and sequence length

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

#39 - add_first doc says timestep but code takes observation

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

#38 - Not enough documentation for EpisodeAdder

Issue - State: open - Opened by drozzy over 4 years ago - 6 comments
Labels: documentation

#37 - Missing pip install dm-env in Quickstart?

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

#36 - Does Acme support Gym Tuple Spaces?

Issue - State: closed - Opened by coreyhahn over 4 years ago - 3 comments

#35 - R2D2: Cast rewards and discounts to the same type as network values.

Pull Request - State: closed - Opened by PPSantos over 4 years ago - 2 comments
Labels: cla: yes

#34 - dm-acme[reverb] installation fail

Issue - State: closed - Opened by EstherXSD over 4 years ago - 6 comments
Labels: question

#33 - Very high CPU usage

Issue - State: closed - Opened by LQNew over 4 years ago - 5 comments

#32 - QuickStart throws attribute error

Issue - State: closed - Opened by yotaro-shimose over 4 years ago

#31 - GymWrapper: deepcopy fails due to its __getattr__ method

Issue - State: closed - Opened by graidl over 4 years ago - 5 comments

#30 - Data type errors with LunarLanderContinuous, MountainCar

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

#29 - MCTS agent: environment in simulation out of sync

Issue - State: closed - Opened by graidl over 4 years ago - 2 comments
Labels: bug

#28 - Cannot run r2d2

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

#27 - TRPO / PPO / SAC implementations

Issue - State: closed - Opened by batu over 4 years ago - 10 comments
Labels: enhancement

#26 - Rendering atari environment

Issue - State: closed - Opened by dcharrezt over 4 years ago - 4 comments
Labels: enhancement

#25 - NN "torso"?

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

#24 - Callback system

Issue - State: closed - Opened by schouhy over 4 years ago - 9 comments

#23 - Error: Casting error when running D4PG

Issue - State: closed - Opened by boogies over 4 years ago

#22 - Some dependencies missing in quickstart

Issue - State: closed - Opened by drozzy over 4 years ago - 7 comments

#21 - Gym Environment ( no available MuJoCo access )

Issue - State: closed - Opened by mosicr over 4 years ago - 7 comments

#20 - Does this support pytorch-based agents?

Issue - State: closed - Opened by drozzy over 4 years ago - 8 comments

#19 - Dead paper link in blog post

Issue - State: closed - Opened by drozzy over 4 years ago - 5 comments
Labels: documentation

#18 - Update documentation and fixes Colab badges

Pull Request - State: closed - Opened by sebtheiler over 4 years ago - 1 comment
Labels: cla: yes

#17 - Fix typos and broken link

Pull Request - State: closed - Opened by sebtheiler over 4 years ago - 5 comments
Labels: cla: yes

#15 - Issues importing acme.tf

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

#14 - Acme Tutorial Won't Start in Colab

Issue - State: closed - Opened by mosicr over 4 years ago - 3 comments

#13 - Launchpad release?

Issue - State: closed - Opened by rlanka4 over 4 years ago - 9 comments

#12 - Contributing

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

#11 - Simple Example with CartPole, MountainCar

Issue - State: closed - Opened by kjacek over 4 years ago - 8 comments

#10 - fix: old command used in tutorial

Pull Request - State: closed - Opened by tnfru over 4 years ago - 3 comments
Labels: cla: yes

#9 - dm-acme[reverb] installation fails

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

#8 - fixes logging of tf.Tensors to CSV files

Pull Request - State: closed - Opened by filangelos over 4 years ago
Labels: cla: yes

#7 - AZLearner: TD vs MSE-to-outcome

Issue - State: closed - Opened by seb314 over 4 years ago - 3 comments

#6 - Fix typos, add more links to examples README

Pull Request - State: closed - Opened by bharatr21 over 4 years ago
Labels: cla: yes

#5 - Update index.md

Pull Request - State: closed - Opened by sudo-owen over 4 years ago - 6 comments
Labels: cla: yes

#4 - Distributed training examples?

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

#3 - add license to source distributions

Pull Request - State: closed - Opened by bollwyvl over 4 years ago - 5 comments
Labels: cla: yes

#1 - error in install reverb

Issue - State: closed - Opened by thunanguyen over 4 years ago - 1 comment
Labels: wontfix