adaptive-transformers-in-rl
popgym
adaptive-transformers-in-rl | popgym | |
---|---|---|
1 | 4 | |
129 | 147 | |
- | 8.8% | |
10.0 | 6.1 | |
about 4 years ago | about 1 month ago | |
Python | Python | |
- | MIT License |
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.
adaptive-transformers-in-rl
-
TransformerXL + PPO Baseline + MemoryGym
Found relevant code at https://github.com/jerrodparker20/adaptive-transformers-in-rl + all code implementations here
popgym
-
What RL library supports custom LSTM and Transformer neural networks to use with algorithms such as PPO?
POPGym is based on RLlib and has two linear transformers and five or six RNN variants, including LSTM. I've found that transformers tend to perform pretty poorly in RL when compared to RNNs.
-
POPGym: Partially Observable Reinforcement Learning
Code: https://github.com/proroklab/popgym
-
TransformerXL + PPO Baseline + MemoryGym
Have you seen this other ICLR paper, POPGym? Paper: https://openreview.net/forum?id=chDrutUTs0K Code: https://github.com/smorad/popgym
-
Partially observable Continuous Control Gym Environment
https://github.com/smorad/popgym contains 15 partially observable gym environments, but they use discrete actino spaces. I've verified that memoryless models (e.g. PPO+MLP) cannot solve these tasks, except for the navigation ones.
What are some alternatives?
DI-engine - OpenDILab Decision AI Engine
recurrent-ppo-truncated-bptt - Baseline implementation of recurrent PPO using truncated BPTT
episodic-transformer-memory-ppo - Clean baseline implementation of PPO using an episodic TransformerXL memory
brain-agent - Brain Agent for Large-Scale and Multi-Task Agent Learning
Gymnasium - An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
ppo-implementation-details - The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.