DeepRL-TensorFlow2
tensorforce
DeepRL-TensorFlow2 | tensorforce | |
---|---|---|
2 | 1 | |
573 | 3,283 | |
- | 0.3% | |
0.0 | 3.0 | |
almost 2 years ago | 29 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
DeepRL-TensorFlow2
-
PPO implementation in TensorFlow2
I've been searching for a clean, good, and understandable implementation of PPO for continuous action space with TF2 witch is understandable enough for me to apply my modifications, but the closest thing that I have found is this code which seems to not work properly even on a simple gym cartpole env (discussed issues in git-hub repo suggest the same problem) so I have some doubts :). I was wondering whether you could recommend an implementation that you trust and suggest :)
-
Question about using tf.stop_gradient in separate Actor-Critic networks for A2C implementation for TF2
I have been looking at this implementation of A2C. Here the author of the code uses stop_gradient only on the critic network at L90 bur not in the actor network L61 for the continuous case. However , it is used both in actor and critic networks for the discrete case. Can someone explain me why?
tensorforce
-
Advice on doing RL for Settlers of Catan?
The most promising approach has been using the TensorForce framework (https://github.com/tensorforce/tensorforce) with a custom environment that represents a simpler game (1v1 against a bot that chooses actions randomly, no trading between players, and fixing discarding to be done automatically and at random).
What are some alternatives?
soft-actor-critic - Re-implementation of Soft-Actor-Critic (SAC) in TensorFlow 2.0
pytorch-a2c-ppo-acktr-gail - PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
TensorFlow2.0-for-Deep-Reinforcement-Learning - TensorFlow 2.0 for Deep Reinforcement Learning. :octopus:
ydata-synthetic - Synthetic data generators for tabular and time-series data
agents - TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
minimalRL - Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
deepdrive - Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
trax - Trax — Deep Learning with Clear Code and Speed
tf2multiagentrl - Clean implementation of Multi-Agent Reinforcement Learning methods (MADDPG, MATD3, MASAC, MAD4PG) in TensorFlow 2.x
action-branching-agents - (AAAI 2018) Action Branching Architectures for Deep Reinforcement Learning