dreamer-pytorch

dreamer-pytorch copied to clipboard

PyTorch now has a TanhTransform class, replacing the old TanhBijector (which was, incidentally, broken with the newest version of pyTorch)

Rohan138

some bug with "python main.py" ~v~

1

Dear authers, after run “python main.py”, there is a error. run 0 already exists. run 1 already exists. run 2 already exists. run 3 already exists. run 4 already exists....

kabuwaniu

Why are observation_embed and action at the same “t” in the rollout_representation function?

7

Hi, I'm confused... In rnns.py，there is a function as follows: def rollout_representation(self, steps: int, obs_embed: torch.Tensor, action: torch.Tensor, prev_state: RSSMState): priors = [] posteriors = [] for t in range(steps):...

thj926

I see that the results for mujoco are posted. What results did you get for the Atari envs? Was the agent able to more-or-less converge after 1 million steps?

arcosin

Very minor bug in RSSM

1

Very minor (and I may have misunderstood): I believe the input to the `stochastic_prior_model` in the `RSSMTransition` class should be `deterministic_size` rather than `hidden_size` (line 76 in `rnns.py`). This doesn't...

alec-tschantz

Does this repo reproduce original result

1

Is this implementation of dreamer verified to work? And did anyone tested if this reproduces result in original paper

buoyancy99

Multi gpu

2

This runs on multiple GPUS. That said, there are some sketchy things: - I just chose num_cpus equal to the number of cpus on my desktop, but IDK what the...

AliengirlLiv

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.3. Release notes Sourced from jinja2's releases. 3.1.3 This is a fix release for the 3.1.x feature branch. Fix for GHSA-h5c8-rqwp-cp95. You are affected if...

dependabot[bot]

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.3. Release notes Sourced from jinja2's releases. 3.1.3 This is a fix release for the 3.1.x feature branch. Fix for GHSA-h5c8-rqwp-cp95. You are affected if...

dependabot[bot]

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.3. Release notes Sourced from jinja2's releases. 3.1.3 This is a fix release for the 3.1.x feature branch. Fix for GHSA-h5c8-rqwp-cp95. You are affected if...

dependabot[bot]