Skip to content

Commit

Permalink
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add notebooks/agents.md
Browse files Browse the repository at this point in the history
e10101 committed Jan 9, 2022
1 parent e0a3fed commit da71ac5
Showing 3 changed files with 27 additions and 8 deletions.
10 changes: 3 additions & 7 deletions Dockerfile
Original file line number Diff line number Diff line change
@@ -1,17 +1,13 @@
#FROM jupyter/tensorflow-notebook:12460db878e3
FROM tensorflow/tensorflow:2.7.0-jupyter
COPY requirements.txt ./
RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

USER root

RUN apt-get update
RUN apt-get update && apt-get upgrade --yes
RUN apt-get install -y python-opengl
RUN apt-get install -y xvfb
RUN apt-get install -y ffmpeg
RUN apt-get install -y freeglut3-dev

RUN pip install pyvirtualdisplay
RUN pip install dm-reverb
RUN pip install jupyterlab
RUN pip install imageio imageio-ffmpeg
COPY requirements.txt ./
RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
18 changes: 18 additions & 0 deletions notebooks/agents.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Agents in the `tf-agents`

## Agents

| Agent (Algorithm) | Description | TFA Module | Action Space | Release | Inventor | Related Agents (or Algorithms) | On-policy / Off-policy |
| ------------------------------------------------------------ | ----------------------------------------------------- | ------------------ | -------------------- | ------- | -------- | ------------------------------------------------------------ | ---------------------- |
| BehavioralCloningAgent | Behavioral Cloning | behavioral_cloning | | | | | |
| CategoricalDqnAgent | Categorical DQN (C51) | categorical_dqn | | | | | |
| CqlSacAgent | CQL-SAC | cql | | | | | |
| DdpgAgent | Deep Deterministic Policy Gradient (DDPG) | ddpg | | | | | |
| [DqnAgent](https://www.tensorflow.org/agents/api_docs/python/tf_agents/agents/DqnAgent) | Deep Q Network | dqn | Discrete | 2013 | DeepMind | | Off-policy |
| [PPOAgent](https://www.tensorflow.org/agents/api_docs/python/tf_agents/agents/PPOAgent) | Proximal Policy Optimization | ppo | Discrete, Continuous | 2017 | OpenAI | ACER (Actor-Critic with Experience Replay), TRPO (Trust Region Policy Optimization) | On-policy |
| [PPOClipAgent](https://www.tensorflow.org/agents/api_docs/python/tf_agents/agents/PPOClipAgent) | PPO with clipped probability ratios | ppo | | | | | |
| [PPOKLPenaltyAgent](https://www.tensorflow.org/agents/api_docs/python/tf_agents/agents/PPOKLPenaltyAgent) | PPO with KL penalty loss | ppo | | | | | |
| ReinforceAgent | REINFORCE | reinforce | | | | | |
| SacAgent | Soft Actor Critic | sas | | | | | |
| TD3 Agent | Twin Delayed Deep Deterministic policy gradient (TD3) | td3 | | | | | |

7 changes: 6 additions & 1 deletion requirements.txt
Original file line number Diff line number Diff line change
@@ -1,3 +1,8 @@
tf-agents
tensorflow-probability
pyglet
pyglet
pyvirtualdisplay
dm-reverb
jupyterlab
imageio
imageio-ffmpeg

0 comments on commit da71ac5

Please sign in to comment.